© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157177
    Prev
    Next
    INDEX
    Explanations

    event

    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_2_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
    ва
    1.61
    ı
    1.35
    ion
    1.19
    ной
    1.16
    ای
    1.10
    le
    1.09
    ik
    1.09
    ie
    1.09
    ри
    1.06
    リ
    1.06
    POSITIVE LOGITS
    genommen
    0.92
     agreeable
    0.91
    ोरेशन
    0.89
     perpetually
    0.88
    вр
    0.88
     Anwendung
    0.87
     solidly
    0.85
    ་
    0.84
    是最
    0.82
    ુ
    0.82
    Activations Density 0.002%

    No Known Activations