© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11997
    Prev
    Next
    INDEX
    Explanations

    content from legal patent filings, particularly patent numbers and related language.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     myſelf
    -2.11
     itſelf
    -2.09
    ^(@)
    -2.05
     Efq
    -2.03
    ſelf
    -2.00
     ―――――
    -1.98
     iſt
    -1.97
     ་་
    -1.95
     ſind
    -1.92
    ſelves
    -1.92
    POSITIVE LOGITS
    ,
    1.19
    <eos>
    1.11
    .
    1.03
    ↵↵
    0.97
    ;
    0.89
     (
    0.89
    :
    0.85
    ↵
    0.84
     
    0.84
     -
    0.79
    Activations Density 25.084%

    No Known Activations