© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220964
    Prev
    Next
    INDEX
    Explanations

    pasar y sus variaciones

    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_10_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
    ą
    0.77
    asına
    0.74
    ā
    0.68
    ای
    0.67
    გან
    0.66
    ę
    0.63
    ?",
    0.62
    ı
    0.61
    ק
    0.61
     şek
    0.60
    POSITIVE LOGITS
    （
    0.62
    自己
    0.59
    0
    0.58
     (
    0.56
     de
    0.56
    RNN
    0.53
    лни
    0.53
    CC
    0.52
    猎
    0.52
     historische
    0.52
    Activations Density 0.005%

    No Known Activations