© 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. 34878
    Prev
    Next
    INDEX
    Explanations

    home advantage

    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
     is
    0.75
    IA
    0.70
    ER
    0.63
    IT
    0.63
    U
    0.63
    DE
    0.62
     Univer
    0.61
    AT
    0.59
    UR
    0.58
    oran
    0.57
    POSITIVE LOGITS
    이지만
    0.82
    ס
    0.79
    ו
    0.72
    大赛
    0.70
    이었다
    0.70
    з
    0.69
    ों
    0.66
     soothe
    0.66
     reelection
    0.66
    મ
    0.65
    Activations Density 0.004%

    No Known Activations