© 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. 141320
    Prev
    Next
    INDEX
    Explanations

    wait for

    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
     краю
    0.59
     vụ
    0.57
     đường
    0.55
     bacon
    0.54
     groene
    0.54
     стране
    0.53
    i
    0.53
     установки
    0.52
     heuristics
    0.52
     gebruikers
    0.52
    POSITIVE LOGITS
     SSm
    0.56
    ζ
    0.56
     Ast
    0.55
    秣
    0.54
    Empleado
    0.53
     Μ
    0.53
     Ζ
    0.52
     Católica
    0.52
     Political
    0.52
     Št
    0.52
    Activations Density 0.001%

    No Known Activations