© 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. 122045
    Prev
    Next
    INDEX
    Explanations

    max_

    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
    in
    0.84
     de
    0.80
     an
    0.79
    ți
    0.67
     is
    0.67
    ं
    0.66
    ри
    0.64
     a
    0.64
    वा
    0.64
     territorial
    0.61
    POSITIVE LOGITS
    H
    0.73
     продажи
    0.72
    ل
    0.69
    К
    0.68
    И
    0.66
    ურთი
    0.66
     звезды
    0.66
    ensions
    0.65
    𝑰
    0.65
    鹘
    0.64
    Activations Density 0.000%

    No Known Activations