© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36152
    Prev
    Next
    INDEX
    Explanations

    subacute, alpine, query

    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
    จะ
    0.73
    很
    0.71
    ق
    0.70
    ק
    0.67
    ب
    0.65
    ل
    0.63
    ä
    0.63
     a
    0.61
     जु
    0.61
    Arqu
    0.60
    POSITIVE LOGITS
     as
    0.80
    ਰ
    0.79
    at
    0.71
    y
    0.71
    യോ
    0.71
    SOCIAL
    0.69
    n
    0.69
     характера
    0.68
    서
    0.68
    ﻱ
    0.67
    Activations Density 0.002%

    No Known Activations