© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219334
    Prev
    Next
    INDEX
    Explanations

    hand tools

    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_47_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
     Chryst
    0.38
    ресенье
    0.36
    Performance
    0.36
    )$\\
    0.35
    Utility
    0.35
    酎
    0.35
     Pretty
    0.34
     Switching
    0.34
    。『
    0.34
     switching
    0.33
    POSITIVE LOGITS
     hand
    1.08
     Hand
    0.91
    Hand
    0.83
    hand
    0.81
    手
    0.77
     हैंड
    0.69
     हाथ
    0.68
    HAND
    0.68
     HAND
    0.66
     hånd
    0.63
    Activations Density 0.000%

    No Known Activations