© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1623
    Prev
    Next
    INDEX
    Explanations

    punctuation separating sentences or parts of sentences and some conjunctions

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mist
    -0.52
     t
    -0.47
     I
    -0.46
     poli
    -0.42
    providedIn
    -0.42
     tanda
    -0.42
     at
    -0.40
     volo
    -0.40
     today
    -0.40
     she
    -0.40
    POSITIVE LOGITS
    脚注の使い方
    0.79
     myſelf
    0.79
     Theſe
    0.77
    |}{$
    0.76
     Monfieur
    0.74
    __':
    0.72
    willigung
    0.71
     itſelf
    0.70
    ArgsConstructor
    0.69
    ſelves
    0.69
    Activations Density 0.633%

    No Known Activations