© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34029
    Prev
    Next
    INDEX
    Explanations

    recent followed by specific information

    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_7_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
     enfoque
    0.60
    ,【
    0.60
     consente
    0.59
     honti
    0.54
    ﾘ
    0.54
     achten
    0.54
     exercer
    0.53
     руки
    0.52
     Ли
    0.52
     ajoute
    0.52
    POSITIVE LOGITS
    as
    0.66
    id
    0.66
     or
    0.64
    us
    0.61
    ia
    0.58
    at
    0.57
    ون
    0.56
    σ
    0.55
    is
    0.54
    ع
    0.54
    Activations Density 0.001%

    No Known Activations