© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91598
    Prev
    Next
    INDEX
    Explanations

    started subtly, innocently, or small

    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
     విశ
    0.60
     penthouse
    0.59
    ﺶ
    0.59
    verses
    0.58
     свобод
    0.57
     счита
    0.57
    ያስ
    0.57
     décrit
    0.54
    scheduled
    0.54
     расходы
    0.54
    POSITIVE LOGITS
    >
    0.71
    `
    0.69
    '
    0.63
    ultura
    0.59
     Camel
    0.55
     estan
    0.55
    می
    0.54
    ær
    0.53
    ()
    0.52
    cz
    0.52
    Activations Density 0.005%

    No Known Activations