© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9948
    Prev
    Next
    INDEX
    Explanations

    terms related to document metadata, legal rulings, nutrition, biology, and medical treatments

    oai_token-act-pair · gemini-2.0-flash

    code and technical writing

    np_max-act · gemini-2.0-flash

    code/XML

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AssemblyCulture
    -1.31
    WriteAttribute
    -1.27
    DockStyle
    -1.26
    IsContent
    -1.23
     متعلقه
    -1.17
     يتيمه
    -1.17
    HomeAsUpEnabled
    -1.16
     للمعارف
    -1.14
     BoxDecoration
    -1.13
    ConstraintMaker
    -1.13
    POSITIVE LOGITS
    порт
    0.70
    PLE
    0.66
     ‘
    0.64
    owiak
    0.59
     simula
    0.56
     καλ
    0.56
    USTER
    0.56
     Me
    0.56
    quester
    0.56
    icorn
    0.55
    Activations Density 20.839%

    No Known Activations