© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19401
    Prev
    Next
    INDEX
    Explanations

    initialization components

    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_15_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
    ון
    0.67
     That
    0.57
     Only
    0.54
     Esa
    0.54
     Life
    0.54
    That
    0.53
     Inicio
    0.53
    >>
    0.53
    >
    0.53
     dedicato
    0.52
    POSITIVE LOGITS
    ebay
    0.57
     pptn
    0.52
    TreeView
    0.51
     funktionieren
    0.50
    鎳
    0.50
     효과
    0.50
     ダンロップ
    0.50
    rahmen
    0.50
    ڑ
    0.49
    кл
    0.49
    Activations Density 0.000%

    No Known Activations