© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162509
    Prev
    Next
    INDEX
    Explanations

    erea, beste, ask

    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_2_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
    も
    1.46
    在
    1.31
    li
    1.12
    ע
    1.09
    ご
    1.08
    ל
    1.05
    一
    1.05
    К
    1.02
     ファイル
    0.99
    י
    0.99
    POSITIVE LOGITS
    h
    1.38
    ;
    1.31
    <0x80>
    1.24
    ,
    1.22
    ia
    1.05
    :
    1.03
    hle
    1.02
    ir
    1.02
    il
    1.00
    ac
    0.96
    Activations Density 0.000%

    No Known Activations