© 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. 231782
    Prev
    Next
    INDEX
    Explanations

    tenfold increase, folding

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ك
    1.12
    ↵↵
    1.10
    َی
    1.01
     benefícios
    0.99
    ﺏ
    0.98
    کي
    0.96
    ９
    0.96
     vaisseaux
    0.95
    ینګ
    0.93
    orderDetails
    0.93
    POSITIVE LOGITS
     in
    1.11
    1.05
     (
    1.00
    $
    0.96
     \
    0.91
     are
    0.91
    س
    0.89
     bulb
    0.87
    ene
    0.86
     land
    0.86
    Activations Density 0.000%

    No Known Activations