© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108922
    Prev
    Next
    INDEX
    Explanations

    concession or conception

    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_1_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
    an
    2.02
    ก
    1.71
    k
    1.59
    '
    1.57
    c
    1.55
     can
    1.51
    r
    1.51
    the
    1.48
    b
    1.48
     was
    1.44
    POSITIVE LOGITS
    Y
    1.04
    IS
    0.88
    YP
    0.87
    3
    0.87
    YH
    0.81
     Bestell
    0.79
     Ejecutivo
    0.78
    Ĵ
    0.78
    Chess
    0.77
    ");//
    0.77
    Activations Density 0.001%

    No Known Activations