© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42004
    Prev
    Next
    INDEX
    Explanations

    Robot or automation system names

    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_3_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
    ไม่
    0.74
     τε
    0.72
    u
    0.72
     Consultado
    0.70
     imprison
    0.67
    পত্র
    0.66
     marzo
    0.66
    ปี
    0.66
     baloncesto
    0.66
    坊
    0.66
    POSITIVE LOGITS
    ン
    0.96
    änder
    0.88
    nö
    0.82
    of
    0.79
    ett
    0.78
    í
    0.78
    н
    0.77
    ai
    0.74
    mx
    0.73
    eks
    0.73
    Activations Density 0.000%

    No Known Activations