© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17680
    Prev
    Next
    INDEX
    Explanations

    Old Montreal

    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_15_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
    যাত্রা
    0.58
     envolvendo
    0.51
    5
    0.50
    যাত্র
    0.49
     xhr
    0.48
    工業
    0.48
    وأضاف
    0.48
     கடந்த
    0.47
     ÷
    0.47
    Ин
    0.46
    POSITIVE LOGITS
     trustworthiness
    0.53
    kert
    0.51
     togetherness
    0.51
    waite
    0.50
    kort
    0.49
     differences
    0.47
    Hour
    0.47
    heus
    0.47
     saltwater
    0.47
    tug
    0.46
    Activations Density 0.000%

    No Known Activations