© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142332
    Prev
    Next
    INDEX
    Explanations

    LIN followed by communication or Q

    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_0_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
    ین
    1.98
    л
    1.88
    ۰
    1.88
    ש
    1.61
    ח
    1.56
    لای
    1.46
    ่
    1.45
    ان
    1.34
     incurable
    1.30
    ِی
    1.30
    POSITIVE LOGITS
    ní
    1.63
    ii
    1.45
    and
    1.43
    d
    1.29
    y
    1.29
    一
    1.28
    ály
    1.27
    的书
    1.25
    t
    1.23
    的文章
    1.23
    Activations Density 0.000%

    No Known Activations