© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46925
    Prev
    Next
    INDEX
    Explanations

    Nazar, REM, narzo, NARS

    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_3_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
    د
    0.99
    <0x80>
    0.79
    it
    0.77
    ви
    0.75
    vý
    0.72
    ۰
    0.72
    næ
    0.70
    spielen
    0.69
    нець
    0.68
    ó
    0.68
    POSITIVE LOGITS
    .
    0.68
     puluh
    0.63
     Bunun
    0.62
    -
    0.62
     બો
    0.61
    かけて
    0.59
     basse
    0.58
     texted
    0.58
    。
    0.57
    思
    0.57
    Activations Density 0.001%

    No Known Activations