© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53660
    Prev
    Next
    INDEX
    Explanations

    president

    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_55_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
     sitting
    3.23
    sitting
    2.86
     Sitting
    2.78
    Sitting
    2.78
     ngồi
    2.05
    坐
    1.97
     сидя
    1.95
     sits
    1.88
     sitzen
    1.80
     앉
    1.75
    POSITIVE LOGITS
     প্রতিফল
    0.36
     Peut
    0.36
    rieb
    0.34
     Miro
    0.33
    diagnostic
    0.32
    }}{\
    0.31
     overlap
    0.31
     আলোক
    0.31
     Roja
    0.31
    toContain
    0.31
    Activations Density 0.007%

    No Known Activations