© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27992
    Prev
    Next
    INDEX
    Explanations

    Vibram soles or myjewishlearning

    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
    at
    0.23
    و
    0.23
    ه
    0.22
    ו
    0.21
    ה
    0.21
    ي
    0.20
    ed
    0.20
    inni
    0.19
    ا
    0.19
    ে
    0.18
    POSITIVE LOGITS
     Насе
    0.19
    _
    0.18
    Beat
    0.17
     Worth
    0.17
     Beat
    0.16
    Meat
    0.16
     Provide
    0.16
     Gesundheit
    0.16
     Roosevelt
    0.16
    Slave
    0.16
    Activations Density 0.003%

    No Known Activations