© 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. 201666
    Prev
    Next
    INDEX
    Explanations

    mesmerized

    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
    ↵
    1.22
    在
    1.02
    ot
    0.99
    Ink
    0.98
    oc
    0.97
    ia
    0.94
    Stim
    0.94
    im
    0.93
     Các
    0.93
    v
    0.91
    POSITIVE LOGITS
    <0xA8>
    1.26
     utilization
    1.09
    <0xBF>
    1.07
     burdensome
    1.06
     lovable
    1.02
    ۔
    0.99
     gleaned
    0.98
     decrement
    0.96
     fueling
    0.96
     cringe
    0.96
    Activations Density 0.000%

    No Known Activations