© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14711
    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_13_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
    n
    0.59
    INA
    0.49
    ক
    0.47
    ari
    0.46
    st
    0.46
    se
    0.45
     unequivocal
    0.45
     aquela
    0.45
    ad
    0.44
     abundant
    0.44
    POSITIVE LOGITS
    有助于
    0.46
    栊
    0.46
    雎
    0.45
     الثلاث
    0.44
     Mulder
    0.44
    助
    0.44
    违反
    0.44
    涘
    0.43
    扞
    0.43
    zęd
    0.43
    Activations Density 0.000%

    No Known Activations