© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36643
    Prev
    Next
    INDEX
    Explanations

    zero-shot / few-shot prompt learning

    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
    ی
    0.87
    ו
    0.83
    LA
    0.71
    CORDS
    0.71
    D
    0.70
    ς
    0.70
    MEM
    0.67
    B
    0.67
    0.67
    ES
    0.66
    POSITIVE LOGITS
    ires
    0.71
    ре
    0.63
    r
    0.62
    il
    0.61
    ität
    0.61
     hypothes
    0.60
    inter
    0.59
    ip
    0.59
    urbed
    0.58
    aría
    0.57
    Activations Density 0.002%

    No Known Activations