© 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. 12490
    Prev
    Next
    INDEX
    Explanations

    database connection parameters

    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
    s
    0.63
    스를
    0.52
     aliqua
    0.51
     bóng
    0.50
    يت
    0.49
    is
    0.49
     đơn
    0.48
    iculis
    0.48
    c
    0.47
    𝓬
    0.47
    POSITIVE LOGITS
     שמ
    0.44
    /...
    0.43
     Memoirs
    0.43
    <unused63>
    0.41
     Hod
    0.41
    
    0.40
     Когда
    0.40
     Odisha
    0.40
    */
    0.39
     Ці
    0.39
    Activations Density 0.000%

    No Known Activations