© 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. 259048
    Prev
    Next
    INDEX
    Explanations

    begin, continue, prepare, attempt, review

    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
    indahan
    0.19
    erweise
    0.19
    Bad
    0.18
    W
    0.18
    das
    0.18
    adin
    0.18
    L
    0.18
    Ä
    0.18
    apse
    0.18
    ßer
    0.18
    POSITIVE LOGITS
    》，
    0.18
     mattis
    0.18
     UCLA
    0.17
     trav
    0.17
     inscribed
    0.17
     зару
    0.16
     franca
    0.16
     kiosk
    0.16
    事项
    0.16
     tlač
    0.16
    Activations Density 0.010%

    No Known Activations