© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230488
    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
    v
    1.52
    im
    1.33
    r
    1.30
    h
    1.23
    ong
    1.21
    ys
    1.21
    ub
    1.16
    s
    1.16
    us
    1.14
    ar
    1.13
    POSITIVE LOGITS
    dır
    1.07
     Në
    0.97
    ザ
    0.95
     نہيں
    0.92
    امة
    0.92
    ן
    0.91
     făcut
    0.89
    ズ
    0.87
     Tijdens
    0.86
     بالټ
    0.86
    Activations Density 0.000%

    No Known Activations