© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58005
    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_2_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
    у
    1.08
    im
    1.02
    र
    0.93
    서
    0.93
    ur
    0.93
    рите
    0.88
    ac
    0.88
    ak
    0.86
    ир
    0.86
    anc
    0.84
    POSITIVE LOGITS
    I
    1.34
    ੀ
    1.00
     інших
    1.00
    㞔
    0.86
    daki
    0.80
    دي
    0.80
    delen
    0.80
    t
    0.80
    䯩
    0.79
     miếng
    0.77
    Activations Density 0.000%

    No Known Activations