© 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. 129807
    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
    ي
    1.13
    '
    1.11
    at
    1.10
    i
    1.05
    ak
    1.03
    uv
    1.00
    ć
    0.98
    2
    0.98
    ul
    0.96
    op
    0.95
    POSITIVE LOGITS
    t
    1.12
    د
    1.02
    ρο
    0.99
    لی
    0.98
    بر
    0.96
    లు
    0.89
    ัน
    0.86
    ும்
    0.84
    ک
    0.84
    in
    0.84
    Activations Density 0.000%

    No Known Activations