© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60139
    Prev
    Next
    INDEX
    Explanations

    things that come to mind

    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_11_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
    с
    0.78
    ур
    0.68
    ن
    0.62
    ব
    0.61
    лана
    0.57
    لک
    0.56
     étoile
    0.56
    자와
    0.56
    ス
    0.56
    س
    0.56
    POSITIVE LOGITS
     i
    0.84
     logics
    0.61
     esimerkiksi
    0.58
    ards
    0.57
     o
    0.56
     IC
    0.54
     되면
    0.54
     flow
    0.54
     כי
    0.54
     by
    0.52
    Activations Density 0.000%

    No Known Activations