© 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. 37763
    Prev
    Next
    INDEX
    Explanations

    Ya Kun Kaya Toast

    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
    to
    0.92
    le
    0.77
    ле
    0.70
    д
    0.67
    ş
    0.64
    sproz
    0.63
    machen
    0.63
    ят
    0.62
    人士
    0.61
    jų
    0.61
    POSITIVE LOGITS
    0
    0.84
    8
    0.75
    I
    0.67
    ิ
    0.66
    9
    0.64
    AN
    0.64
    :
    0.62
    :',
    0.62
    4
    0.62
    ：
    0.61
    Activations Density 0.005%

    No Known Activations