© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18449
    Prev
    Next
    INDEX
    Explanations

    four

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chessboard
    0.38
    dbl
    0.38
    textbackslash
    0.38
     माइक्रो
    0.36
    ͈
    0.36
    chessboard
    0.35
    vstack
    0.35
    avro
    0.35
    otions
    0.35
    collide
    0.35
    POSITIVE LOGITS
    四
    1.27
     four
    1.26
     Four
    1.21
    Four
    1.20
    four
    1.17
     FOUR
    1.17
    FOUR
    1.16
     четырех
    1.11
     चार
    1.10
     四
    1.10
    Activations Density 0.050%

    No Known Activations