© 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. 201238
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    a
    1.61
    n
    1.27
    t
    1.26
    q
    1.22
    st
    1.20
    r
    1.18
    CH
    1.16
    o
    1.13
    in
    1.11
    c
    1.09
    POSITIVE LOGITS
    ку
    1.08
     cárc
    1.03
    σό
    1.00
    기
    0.91
    тари
    0.90
    ش
    0.90
     tenements
    0.89
     ovipares
    0.89
     connaissances
    0.88
     soluções
    0.88
    Activations Density 0.000%

    No Known Activations