© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205569
    Prev
    Next
    INDEX
    Explanations

    Montag, Robinson, Scout, Liesel, Esperanza

    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_6_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
    t
    1.29
    n
    0.99
    p
    0.97
    on
    0.96
    ہ
    0.95
    са
    0.92
    ца
    0.92
    sa
    0.90
    ڈ
    0.87
    ку
    0.86
    POSITIVE LOGITS
    ।'
    0.79
    Externe
    0.75
    '
    0.71
     ।
    0.70
    。
    0.69
     vuttam
    0.68
    Explorer
    0.68
     nerada
    0.67
    '।
    0.67
    0.66
    Activations Density 0.013%

    No Known Activations