© 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. 42821
    Prev
    Next
    INDEX
    Explanations

    categorizing lists

    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
    فكير
    0.43
    ަށް
    0.40
    וּ
    0.40
    ör
    0.39
     składa
    0.38
    Clinic
    0.38
    𝚌
    0.38
    clinic
    0.38
    ियर
    0.37
    imize
    0.37
    POSITIVE LOGITS
     Tonight
    0.40
    옹
    0.39
    GameBoard
    0.38
     pivot
    0.38
     Geelong
    0.38
     IMAX
    0.38
    哄
    0.38
     Camero
    0.37
     두
    0.37
     LIN
    0.37
    Activations Density 0.014%

    No Known Activations