© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138910
    Prev
    Next
    INDEX
    Explanations

    arabica

    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_12_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
    para
    0.50
    nonpayable
    0.48
    дается
    0.47
    Przyp
    0.46
    .$;
    0.46
    .);
    0.46
    rzez
    0.45
    ducible
    0.45
    أ
    0.44
    顯
    0.44
    POSITIVE LOGITS
     Siamese
    0.63
     Yoda
    0.60
     oyster
    0.55
     boulder
    0.54
     Disney
    0.54
     Seattle
    0.54
     SALE
    0.54
     starg
    0.54
    inse
    0.54
     ER
    0.53
    Activations Density 0.001%

    No Known Activations