© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44341
    Prev
    Next
    INDEX
    Explanations

    technical terms and categories

    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
    isiert
    0.40
    ertime
    0.40
    َيْ
    0.39
     Gewerks
    0.38
     unterschied
    0.38
    different
    0.38
    alingrad
    0.38
    hely
    0.37
    LETIN
    0.37
    Different
    0.37
    POSITIVE LOGITS
    док
    0.40
     incentivize
    0.39
     episódio
    0.37
    ར་
    0.37
     (<
    0.36
     पढ़ेंगे
    0.36
     seduce
    0.36
     terd
    0.36
     ગાં
    0.36
     see
    0.36
    Activations Density 0.010%

    No Known Activations