© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199545
    Prev
    Next
    INDEX
    Explanations

    marks fraction

    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_9_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
    ма
    1.05
    м
    0.97
    го
    0.91
     alebo
    0.89
    গ
    0.89
    ക
    0.89
    ন
    0.88
    на
    0.86
    ni
    0.82
    ба
    0.82
    POSITIVE LOGITS
    an
    0.86
    ால்
    0.82
    ({\
    0.77
    aris
    0.76
    ag
    0.74
     Ար
    0.74
     rumin
    0.71
     bullion
    0.71
    uhe
    0.71
     geotechnical
    0.70
    Activations Density 0.000%

    No Known Activations