© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89131
    Prev
    Next
    INDEX
    Explanations

    abschätzen von werten

    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_11_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
    baren
    0.57
    ber
    0.55
    ();
    0.55
    די
    0.54
    ၊
    0.53
     Üniversitesi
    0.51
     நாளில்
    0.51
     dupa
    0.51
    嘏
    0.50
    beri
    0.50
    POSITIVE LOGITS
    t
    0.60
     выяс
    0.59
     согла
    0.58
     игро
    0.58
     ассо
    0.58
     интере
    0.58
     работа
    0.55
     cadastro
    0.55
     экономи
    0.55
     cadast
    0.54
    Activations Density 0.000%

    No Known Activations