© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79382
    Prev
    Next
    INDEX
    Explanations

    squawking, squish, squat, squirtle

    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_0_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
    ,
    1.87
    ่
    1.85
    р
    1.78
    p
    1.77
     a
    1.68
    a
    1.55
    c
    1.46
    ר
    1.45
    b
    1.39
    ও
    1.35
    POSITIVE LOGITS
    та
    1.45
    О
    1.34
    ج
    1.28
     is
    1.21
     intéressant
    1.20
     on
    1.20
    芢
    1.20
    tage
    1.18
    Во
    1.17
     لأ
    1.17
    Activations Density 0.000%

    No Known Activations