© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80202
    Prev
    Next
    INDEX
    Explanations

    stats for models

    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_0_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
    ა
    2.06
    a
    1.83
    ق
    1.75
    ਾ
    1.75
    ী
    1.73
    ע
    1.60
    в
    1.56
    en
    1.54
    is
    1.49
    ic
    1.49
    POSITIVE LOGITS
    يل
    1.43
    ished
    1.24
    illä
    1.20
    üler
    1.20
    ็ก
    1.13
    .
    1.13
    ัด
    1.09
    apas
    1.09
     공개
    1.08
    ık
    1.06
    Activations Density 0.001%

    No Known Activations