© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134353
    Prev
    Next
    INDEX
    Explanations

    stock, Lust, фон

    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
    il
    2.16
    ur
    1.88
    ad
    1.77
    b
    1.72
    ir
    1.68
    i
    1.52
    x
    1.47
    ine
    1.41
    u
    1.36
    us
    1.32
    POSITIVE LOGITS
    ного
    0.88
    ně
    0.88
    لي
    0.87
    ری
    0.86
     Darüber
    0.86
     исследова
    0.85
    ник
    0.82
    čně
    0.82
     instancia
    0.82
    着
    0.81
    Activations Density 0.000%

    No Known Activations