© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47543
    Prev
    Next
    INDEX
    Explanations

    check followed by inquiry

    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
    ="
    0.57
     godina
    0.57
     effektiv
    0.56
    ere
    0.55
     Temperatur
    0.54
     RMSE
    0.53
     verpflicht
    0.52
    ()
    0.52
    6
    0.52
     Aenean
    0.51
    POSITIVE LOGITS
     که
    0.51
     Лит
    0.51
    ኵ
    0.50
    اک
    0.49
    u
    0.47
     secretory
    0.47
    чный
    0.46
    nelles
    0.45
    tait
    0.43
    Нет
    0.43
    Activations Density 0.015%

    No Known Activations