© 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. 102934
    Prev
    Next
    INDEX
    Explanations

    TNM staging classification

    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
    A
    1.35
    T
    1.24
    1.17
    ↵↵
    1.16
    د
    1.13
    S
    1.08
    '
    1.05
    C
    1.04
    g
    1.03
    W
    1.02
    POSITIVE LOGITS
    n
    1.30
    야
    1.19
    ки
    1.10
    에
    1.06
     be
    0.93
    اً
    0.92
     as
    0.89
    at
    0.86
     at
    0.86
    aries
    0.85
    Activations Density 0.000%

    No Known Activations