© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43471
    Prev
    Next
    INDEX
    Explanations

    Black Comedy, Black people, Brown trousers

    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_3_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
    는
    0.91
    ка
    0.83
    ρα
    0.81
    ма
    0.77
    λα
    0.76
    и
    0.76
    га
    0.75
    も
    0.75
    ので
    0.74
    도
    0.73
    POSITIVE LOGITS
    s
    0.97
    n
    0.94
    et
    0.93
    t
    0.87
    m
    0.86
    0.83
     for
    0.68
    v
    0.68
    ek
    0.66
    u
    0.65
    Activations Density 0.005%

    No Known Activations