© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10680
    Prev
    Next
    INDEX
    Explanations

    HTML and code snippets containing table structures and library imports

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <tbody>
    -1.16
     rather
    -0.45
    +#+#
    -0.44
     absolute
    -0.42
    itemize
    -0.40
     or
    -0.40
     instead
    -0.40
    transQ
    -0.40
     Gra
    -0.40
     tárgy
    -0.40
    POSITIVE LOGITS
    <bos>
    0.98
    ConstraintMaker
    0.84
     uſe
    0.72
    ſelves
    0.71
     faſt
    0.69
    جغرافيا
    0.68
     itſelf
    0.68
     raiſ
    0.68
     ―――――
    0.67
     myſelf
    0.67
    Activations Density 0.226%

    No Known Activations