© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105504
    Prev
    Next
    INDEX
    Explanations

    biological cultures

    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_1_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
    (
    1.16
    л
    1.09
    .
    1.02
    4
    0.97
    iel
    0.96
    à
    0.96
    itt
    0.95
    ati
    0.92
     are
    0.91
    ies
    0.89
    POSITIVE LOGITS
    ur
    0.96
     construido
    0.90
     gebru
    0.89
    SDLCheck
    0.89
    a
    0.89
     sech
    0.87
    ას
    0.86
    ي
    0.84
    ttino
    0.83
     nhàng
    0.83
    Activations Density 0.000%

    No Known Activations