© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    HTML tag attributes that refer to links

    oai_token-act-pair · gemini-2.0-flash

    less common or archaic characters and symbols

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

    web page code

    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
     c
    -0.49
     u
    -0.48
    InteropServices
    -0.48
     t
    -0.46
     
    -0.44
    ULUS
    -0.43
     m
    -0.43
     M
    -0.42
     univers
    -0.42
     T
    -0.41
    POSITIVE LOGITS
     Monfieur
    0.83
     Theſe
    0.78
     Houſe
    0.78
     Efq
    0.75
     ་་
    0.75
     ―――――
    0.75
     Jefus
    0.74
     Anſ
    0.73
     iſt
    0.73
     faſt
    0.73
    Activations Density 0.088%

    No Known Activations