© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135255
    Prev
    Next
    INDEX
    Explanations

    dwindled

    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
    Negative Logits
    is
    1.05
     are
    1.02
    es
    0.98
    al
    0.96
    ০
    0.96
    ０
    0.96
     at
    0.95
     ০
    0.94
     seront
    0.93
     infarct
    0.91
    POSITIVE LOGITS
    that
    1.77
    1
    1.63
    2
    1.28
    sp
    1.07
    remove
    1.06
    they
    1.06
    That
    1.05
    ным
    1.00
    her
    1.00
    total
    1.00
    Activations Density 0.000%

    No Known Activations