© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45718
    Prev
    Next
    INDEX
    Explanations

    centering

    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_22_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
     মুহূর্ত
    0.39
    ึ
    0.39
    髙
    0.39
     관계로
    0.39
    數學
    0.38
    <sup>
    0.38
    riso
    0.37
    jer
    0.37
    multicolumn
    0.37
    監査
    0.37
    POSITIVE LOGITS
     তাদের
    0.47
    ॉप्टर
    0.46
     их
    0.45
    "]:
    0.43
    ()");
    0.42
     onları
    0.42
     inventions
    0.41
     لیست
    0.40
    tsioon
    0.40
     direcciones
    0.40
    Activations Density 0.000%

    No Known Activations