© 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. 130082
    Prev
    Next
    INDEX
    Explanations

    client relationships

    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
    ě
    1.31
     alterações
    1.01
     Alguns
    0.97
     Když
    0.95
     comentários
    0.95
    ur
    0.93
     redução
    0.93
     Não
    0.91
     Após
    0.90
     neće
    0.89
    POSITIVE LOGITS
    the
    1.04
    c
    1.02
    ใน
    0.94
     in
    0.92
    在
    0.89
    の
    0.88
    in
    0.88
    m
    0.87
    t
    0.80
    an
    0.79
    Activations Density 0.002%

    No Known Activations