© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203583
    Prev
    Next
    INDEX
    Explanations

    rails routing and generation

    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_12_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
    сторінку
    0.21
     právě
    0.21
    <unused674>
    0.21
    тину
    0.21
     اغلب
    0.21
     Bia
    0.20
     ассоциа
    0.20
    나
    0.20
    ಸೆ
    0.19
    ামিন
    0.19
    POSITIVE LOGITS
    ll
    0.22
     inverses
    0.20
     hobbies
    0.20
     oleks
    0.20
    idän
    0.20
    row
    0.19
     chancellor
    0.19
    莖
    0.19
     slapping
    0.19
     difficol
    0.19
    Activations Density 0.000%

    No Known Activations