© 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. 164606
    Prev
    Next
    INDEX
    Explanations

    points, features, and speed

    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
    st
    0.18
     is
    0.16
    sp
    0.15
     Thread
    0.15
     API
    0.14
    scheduler
    0.14
     ;
    0.14
    has
    0.14
    ipe
    0.13
    lare
    0.13
    POSITIVE LOGITS
    飭
    0.16
    ⅾ
    0.15
     velocidad
    0.15
     disposit
    0.15
    '،
    0.15
    力量
    0.15
     եր
    0.15
     அம்ச
    0.15
     швидко
    0.15
    Ԁ
    0.14
    Activations Density 0.001%

    No Known Activations