© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6059
    Prev
    Next
    INDEX
    Explanations

    historical or scientific descriptions of inventions, particularly those referencing dates and materials.

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or software

    np_token-act-pair-logits · gpt-4o-mini

    Scientific/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.57
    kura
    -0.47
    atguigu
    -0.47
     ammonium
    -0.47
    anmar
    -0.46
     draining
    -0.46
    ignoire
    -0.44
    igata
    -0.44
    blog
    -0.43
     Anatomy
    -0.43
    POSITIVE LOGITS
     ComVisible
    0.65
     AttributeSet
    0.62
    #+#
    0.60
    withIdentifier
    0.60
     Normdatei
    0.60
     AssemblyVersion
    0.59
    ViewImports
    0.59
    TargetException
    0.58
    NewUrlParser
    0.56
    UrlResolution
    0.56
    Activations Density 2.943%

    No Known Activations