© 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. 46053
    Prev
    Next
    INDEX
    Explanations

    suspect

    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
    <0x80>
    0.64
     jí
    0.56
    deps
    0.56
    กว่า
    0.55
    to
    0.54
    laan
    0.54
    GU
    0.53
    一点
    0.53
     ∈
    0.53
    <0x8C>
    0.53
    POSITIVE LOGITS
    </h2>
    0.88
    <0x0D>
    0.87
    یت
    0.82
    </b>
    0.81
    it
    0.75
    س
    0.68
    ক
    0.67
    ‬
    0.67
    ка
    0.65
    itze
    0.64
    Activations Density 0.000%

    No Known Activations