© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10536
    Prev
    Next
    INDEX
    Explanations

    one word

    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_40_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
    whites
    0.41
     steps
    0.41
    WM
    0.41
     pasos
    0.39
     adults
    0.38
    بيض
    0.38
    足を
    0.38
    步
    0.37
     whites
    0.37
     Whites
    0.37
    POSITIVE LOGITS
     tail
    1.09
     Tail
    0.97
    Tail
    0.96
     tailed
    0.95
    tail
    0.94
     tails
    0.92
    尾
    0.92
    tailed
    0.85
     Tails
    0.84
    tails
    0.76
    Activations Density 0.023%

    No Known Activations