© 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. 108161
    Prev
    Next
    INDEX
    Explanations

    inspector titles and names

    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
     to
    1.95
    ED
    1.34
     on
    1.31
    ش
    1.22
    क
    1.15
    ن
    1.15
    या
    1.09
    ח
    1.08
    k
    1.07
    ন
    1.05
    POSITIVE LOGITS
    و
    1.37
    2
    1.07
    ні
    1.05
    łączy
    0.98
     છેલ્લા
    0.97
    ו
    0.96
     uniformed
    0.93
    ﻓ
    0.92
     ника
    0.91
    3
    0.90
    Activations Density 0.000%

    No Known Activations