© 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. 83176
    Prev
    Next
    INDEX
    Explanations

    temperatures or signatures Added

    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
    ة
    1.90
    ing
    1.48
     by
    1.40
     for
    1.34
     on
    1.34
    ور
    1.32
    ab
    1.29
    _
    1.29
    ل
    1.23
    า
    1.19
    POSITIVE LOGITS
    ف
    1.48
    یم
    1.45
    ються
    1.35
     excre
    1.35
     prefque
    1.31
     avaient
    1.30
    ючи
    1.30
    نی
    1.27
     étudier
    1.26
    тэй
    1.25
    Activations Density 0.000%

    No Known Activations