© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1297
    Prev
    Next
    INDEX
    Explanations

    contract, full-time, part-time

    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_39_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
    可选
    0.44
    潦
    0.39
    IONAL
    0.39
    Graduate
    0.36
     पव
    0.35
    liny
    0.35
    飆
    0.35
    阖
    0.35
    TxtArea
    0.34
    Же
    0.34
    POSITIVE LOGITS
     digit
    0.48
    mits
    0.45
    Digit
    0.43
    ्यो
    0.42
     निकलते
    0.39
    digit
    0.38
     uranium
    0.38
     unidades
    0.38
     keratin
    0.38
     رشته
    0.38
    Activations Density 0.003%

    No Known Activations