© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126314
    Prev
    Next
    INDEX
    Explanations

    api ens

    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_3_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
    ar
    0.90
    ו
    0.87
    in
    0.85
    n
    0.84
    o
    0.81
    en
    0.80
    u
    0.78
    as
    0.74
    y
    0.74
    t
    0.73
    POSITIVE LOGITS
     turistas
    0.75
     của
    0.75
    רי
    0.71
    ）、
    0.70
     の
    0.68
    ру
    0.67
    <0x0D>
    0.67
    ینی
    0.67
    ຂອງ
    0.66
     של
    0.66
    Activations Density 0.000%

    No Known Activations