© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5060
    Prev
    Next
    INDEX
    Explanations

    HAL_Init()

    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_40_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
    ɽ
    0.18
     ease
    0.17
     рациона
    0.17
     കേന്ദ്ര
    0.17
     Importing
    0.17
    svg
    0.17
     smut
    0.17
    ೮
    0.17
     землю
    0.17
     ration
    0.17
    POSITIVE LOGITS
     जोकि
    0.20
    ຂໍ້ມ
    0.20
    Thoughts
    0.20
     platform
    0.19
     TEAM
    0.19
     платфор
    0.19
     التف
    0.19
    த்தி
    0.18
    不得不
    0.18
     объяви
    0.18
    Activations Density 0.000%

    No Known Activations