© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134263
    Prev
    Next
    INDEX
    Explanations

    rewrite, rephrasing, or language conversion

    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_6_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
     for
    1.12
     figs
    1.09
     be
    0.89
     fig
    0.84
     I
    0.82
     ر
    0.81
    _
    0.81
     about
    0.80
    ر
    0.79
     by
    0.79
    POSITIVE LOGITS
    عی
    0.84
    تح
    0.80
    헤
    0.79
    has
    0.79
    ஜ்மஹால்
    0.79
    に
    0.79
    ри
    0.78
    μα
    0.77
    n
    0.77
     नव्हते
    0.76
    Activations Density 0.008%

    No Known Activations