© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 2834
    Prev
    Next
    INDEX
    Explanations

    prepositions, conjunctions, and numerical values surrounding the words "time", "steps", "methods", "here" and "of"

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash

    say "punctuation"

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     myſelf
    -2.11
     itſelf
    -1.99
    ſelves
    -1.90
     Efq
    -1.86
     ་་
    -1.85
    ſelf
    -1.84
     ―――――
    -1.72
     Anſ
    -1.71
     raiſ
    -1.71
     ſind
    -1.71
    POSITIVE LOGITS
    .
    1.81
    ;
    1.75
    ?
    1.52
    !
    1.42
    ,
    1.33
    :
    1.16
    —
    1.09
    <eos>
    1.03
    。
    0.99
     ,
    0.98
    Activations Density 13.454%

    No Known Activations