© 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. 42226
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    Didn
    0.34
    ▿
    0.32
     наш
    0.32
    DejaVu
    0.31
    tabControl
    0.31
     wprowad
    0.31
     Daryl
    0.30
     THEIR
    0.30
    ^{(
    0.30
     LAKE
    0.30
    POSITIVE LOGITS
     فاط
    0.34
     antib
    0.32
    গ্রাম
    0.32
    elden
    0.31
     cadres
    0.31
    StatusInternal
    0.31
    orene
    0.31
    ッシ
    0.31
    wati
    0.31
    atorias
    0.30
    Activations Density 0.003%

    No Known Activations