© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46289
    Prev
    Next
    INDEX
    Explanations

    Call of Duty

    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_3_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
    as
    1.34
    an
    1.19
    is
    1.09
    are
    1.02
    t
    1.00
    er
    0.95
     as
    0.93
    m
    0.93
    os
    0.91
    Call
    0.90
    POSITIVE LOGITS
    ي
    0.92
    ד
    0.84
    י
    0.80
    יים
    0.77
     sencillo
    0.76
    -
    0.75
    िन
    0.74
     cách
    0.74
     REGIUNI
    0.74
     ścian
    0.74
    Activations Density 0.001%

    No Known Activations