© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12324
    Prev
    Next
    INDEX
    Explanations

    jobs and credit

    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_13_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
    และ
    0.15
    Mode
    0.14
    Vertex
    0.14
    Stanford
    0.14
    MOTOR
    0.13
     andRow
    0.13
    Magic
    0.13
    ∥
    0.13
     και
    0.13
    Road
    0.13
    POSITIVE LOGITS
    كون
    0.16
     diciendo
    0.15
    كس
    0.15
     времена
    0.14
     sosyal
    0.13
    就业
    0.13
     solen
    0.13
    وك
    0.13
    peration
    0.13
    boru
    0.13
    Activations Density 0.017%

    No Known Activations