© 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. 200745
    Prev
    Next
    INDEX
    Explanations

    ukulele

    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
    a
    1.02
    와의
    0.89
    아
    0.79
    ка
    0.77
    च्या
    0.75
     tubs
    0.75
    मा
    0.74
    НА
    0.74
    ब
    0.73
    ק
    0.73
    POSITIVE LOGITS
    。
    1.10
     {
    0.98
    يد
    0.88
    <0x80>
    0.88
    。)
    0.86
    }
    0.86
     I
    0.84
    。”
    0.83
    ។
    0.82
    {~
    0.82
    Activations Density 0.000%

    No Known Activations