© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38938
    Prev
    Next
    INDEX
    Explanations

    zipfile or ZipRecruiter

    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
     μία
    0.68
    finished
    0.63
    고
    0.63
    ва
    0.61
    از
    0.61
    قار
    0.60
    不然
    0.59
    اب
    0.58
    قف
    0.58
    ل
    0.58
    POSITIVE LOGITS
    s
    0.73
    IOT
    0.70
    ের
    0.70
    _
    0.69
    HEL
    0.68
    IX
    0.67
     ktorý
    0.64
     is
    0.64
    ET
    0.63
    ,
    0.62
    Activations Density 0.001%

    No Known Activations