© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56477
    Prev
    Next
    INDEX
    Explanations

    professional-grade

    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_11_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
     seleção
    0.65
     bakers
    0.62
    о
    0.62
     kucing
    0.60
    ింది
    0.60
     Ramesh
    0.59
     snowflakes
    0.59
    ంపు
    0.59
     lobes
    0.58
     cores
    0.58
    POSITIVE LOGITS
    (
    0.73
    of
    0.67
    t
    0.58
    crow
    0.57
    Value
    0.56
    similar
    0.54
    seems
    0.54
    import
    0.54
    cenia
    0.54
    closing
    0.53
    Activations Density 0.001%

    No Known Activations