© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    code snippets and keywords relating to HTML forms, Javascript, and Django

    oai_token-act-pair · gemini-2.0-flash

    forms and serialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    IsMutable
    -0.97
    +#+#
    -0.89
     defaultstate
    -0.89
     NSCoder
    -0.89
     الحره
    -0.88
    ValueStyle
    -0.88
    contentLoaded
    -0.88
    bootstrapcdn
    -0.86
    mbic
    -0.84
    ConstraintMaker
    -0.83
    POSITIVE LOGITS
    IFER
    0.40
    hofer
    0.38
    bor
    0.38
    leqq
    0.38
     rep
    0.37
     eccell
    0.37
    сла
    0.37
     furent
    0.36
    handleSubmit
    0.35
    gott
    0.35
    Activations Density 0.539%

    No Known Activations