© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13142
    Prev
    Next
    INDEX
    Explanations

    punctuation and common sentence structure markers in multi-lingual text, especially commas, parenthesis, and sentence endings

    oai_token-act-pair · gemini-2.0-flash

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    -3.45
     purpoſe
    -3.45
     Efq
    -3.36
     Monfieur
    -3.33
     itſelf
    -3.31
     pleaſure
    -3.25
     Majefty
    -3.22
     ſeveral
    -3.20
     Reſ
    -3.20
     ſtate
    -3.19
    POSITIVE LOGITS
    ↵
    1.51
    ↵↵
    1.48
     
    1.30
     de
    1.29
    <eos>
    1.20
     la
    1.16
     se
    1.14
     d
    1.12
     "
    1.10
     que
    1.09
    Activations Density 2.057%

    No Known Activations