© 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. 25124
    Prev
    Next
    INDEX
    Explanations

    Foreign Function Interface

    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
    ма
    0.86
    ين
    0.86
    я
    0.77
    ਰ
    0.71
    었다
    0.70
    f
    0.69
    ق
    0.69
    어서
    0.68
    r
    0.68
    ര
    0.68
    POSITIVE LOGITS
    anath
    0.66
    aní
    0.63
    <unused2140>
    0.63
    ด์
    0.63
     EMPLOY
    0.63
    หลากหลาย
    0.61
     ध्वनि
    0.61
    เชิง
    0.61
     unimagin
    0.61
     incentiv
    0.60
    Activations Density 0.000%

    No Known Activations