© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 11587
    Prev
    Next
    INDEX
    Explanations

    code, html tags, URLs, or words related to web design

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    .');
    -1.28
    ?”,
    -1.21
    .')
    -1.16
    .");
    -1.15
    .
    -1.13
    ?')
    -1.13
    ."),
    -1.12
    .”)
    -1.12
    ).”
    -1.11
    ?
    -1.11
    POSITIVE LOGITS
     myſelf
    1.30
     itſelf
    1.21
     Jefus
    1.13
     Efq
    1.09
     himſelf
    1.07
     Monfieur
    1.06
     ſeveral
    1.01
     purpoſe
    1.00
     themſelves
    1.00
     raiſ
    0.98
    Activations Density 4.892%

    No Known Activations