© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30068
    Prev
    Next
    INDEX
    Explanations

    correo electrónico

    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_10_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
    ine
    0.68
     I
    0.65
    edas
    0.61
    iamiento
    0.57
    ich
    0.56
     cust
    0.56
    ic
    0.54
    <0xC2>
    0.54
     wheat
    0.54
    ন্যা
    0.53
    POSITIVE LOGITS
    ט
    0.71
    ڦ
    0.70
    ⸩
    0.66
    ों
    0.66
    Чер
    0.63
    》。
    0.63
    》
    0.62
    ತ್ಮ
    0.59
    ‬
    0.59
    தெ
    0.59
    Activations Density 0.000%

    No Known Activations