© 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. 205340
    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
    1.23
     is
    1.10
    is
    1.05
    ir
    1.00
     can
    0.99
    ara
    0.98
    i
    0.96
    EN
    0.88
     are
    0.88
     =
    0.84
    POSITIVE LOGITS
    ון
    1.20
    تي
    1.02
    тон
    1.02
    تين
    1.00
    လည်း
    0.99
    高的
    0.97
     AppMethodBeat
    0.96
    مان
    0.95
    مر
    0.95
    حي
    0.94
    Activations Density 0.000%

    No Known Activations