© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142451
    Prev
    Next
    INDEX
    Explanations

    raster

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    蹄
    0.40
    hold
    0.38
    ダメ
    0.38
     domestic
    0.37
     Domestic
    0.37
     tiki
    0.35
     বর
    0.34
     numerically
    0.34
    TabText
    0.34
    旮
    0.34
    POSITIVE LOGITS
    RAS
    0.44
     рас
    0.43
     RAS
    0.42
    ST
    0.42
     ras
    0.42
     google
    0.40
    Ras
    0.40
     Ras
    0.40
    DBES
    0.39
    Raster
    0.39
    Activations Density 0.001%

    No Known Activations