© 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. 232500
    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
    r
    1.31
    on
    1.13
    as
    1.13
    d
    1.03
    at
    1.02
    ต
    0.95
    a
    0.92
     on
    0.91
    g
    0.88
    niveau
    0.86
    POSITIVE LOGITS
    0
    1.32
    ۰
    1.14
    いて
    0.99
    ।
    0.98
    1
    0.96
    I
    0.96
    א
    0.95
    ל
    0.94
    IC
    0.93
    HO
    0.89
    Activations Density 0.000%

    No Known Activations