© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146151
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    land
    1.06
    습니다
    1.05
    I
    1.03
    ore
    0.97
    ia
    0.97
    light
    0.97
    glazed
    0.97
    ling
    0.95
    kwik
    0.95
     práct
    0.95
    POSITIVE LOGITS
    на
    1.92
    at
    1.91
    و
    1.77
    и
    1.45
    et
    1.44
    v
    1.42
    р
    1.42
    of
    1.39
    ู
    1.35
    в
    1.34
    Activations Density 0.000%

    No Known Activations