© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    conjunctions, pronouns and prepositions that connect ideas in sentences.

    oai_token-act-pair · gemini-2.0-flash

    Politics

    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
    -
    -0.93
    '
    -0.88
    to
    -0.87
    ↵↵
    -0.83
    .
    -0.81
    ’
    -0.81
    2
    -0.80
    l
    -0.80
    for
    -0.80
    g
    -0.79
    POSITIVE LOGITS
    ^(@)
    1.73
    ConstraintMaker
    1.52
     autorytatywna
    1.50
    RenderAtEndOf
    1.50
     Efq
    1.48
     ligiloj
    1.47
     Roskov
    1.47
    setVerticalGroup
    1.47
     الرياضيه
    1.46
    AndEndTag
    1.46
    Activations Density 11.308%

    No Known Activations