© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45170
    Prev
    Next
    INDEX
    Explanations

    combine dry ingredients

    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_22_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
    weather
    0.14
    бий
    0.13
    ocks
    0.13
    cony
    0.13
    edged
    0.13
    Con
    0.13
     Fisk
    0.13
    击
    0.13
    Waiter
    0.13
    queued
    0.13
    POSITIVE LOGITS
     dunia
    0.15
    獐
    0.15
     يساوي
    0.15
     extrapolation
    0.15
     inbuilt
    0.15
     kJ
    0.14
     диапа
    0.14
     pemasaran
    0.14
     portfolio
    0.14
    空间
    0.14
    Activations Density 0.036%

    No Known Activations