© 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. 25518
    Prev
    Next
    INDEX
    Explanations

    refractory

    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
    u
    1.12
    á
    0.88
    <unused2175>
    0.77
    τη
    0.76
    ó
    0.75
    ación
    0.75
    ão
    0.74
    <unused2104>
    0.73
    ttet
    0.72
    rie
    0.72
    POSITIVE LOGITS
    מו
    0.88
    い
    0.82
    ﻒ
    0.73
    な
    0.71
    ان
    0.70
    Data
    0.69
     biaya
    0.68
    Bailey
    0.68
    (“
    0.68
    बात
    0.67
    Activations Density 0.008%

    No Known Activations