© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204588
    Prev
    Next
    INDEX
    Explanations

    open weights AI assistant

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    운
    0.40
    hatta
    0.40
    िग
    0.39
    運
    0.38
    ダン
    0.37
    莗
    0.37
     জগতে
    0.37
    operatively
    0.36
     Poa
    0.36
    KEYS
    0.36
    POSITIVE LOGITS
    Enroll
    0.38
     Enroll
    0.38
     GN
    0.38
     Rib
    0.37
     clears
    0.37
     Cuban
    0.37
     nii
    0.36
    ڼ
    0.36
     dye
    0.36
    NIR
    0.36
    Activations Density 0.008%

    No Known Activations