© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14382
    Prev
    Next
    INDEX
    Explanations

    language related to change in amount

    oai_token-act-pair · gemini-2.0-flash

    occurrences and variations of the word "by"

    np_token-act-pair-logits · gpt-4o-mini

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    abestanden
    -0.62
     hindurch
    -0.56
    IntoConstraints
    -0.56
    πάρχ
    -0.54
     ProtoMessage
    -0.49
    parsedMessage
    -0.47
    RenderAtEndOf
    -0.46
    yves
    -0.46
    __':
    -0.44
    ագրություններ
    -0.44
    POSITIVE LOGITS
     by
    2.66
    by
    1.81
     oleh
    1.72
     By
    1.65
    By
    1.52
     BY
    1.39
     ידי
    1.34
     توسط
    1.32
     getBy
    1.14
    ListBy
    1.12
    Activations Density 2.524%

    No Known Activations