© 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. 233751
    Prev
    Next
    INDEX
    Explanations

    cleaning items

    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
     التاريخ
    0.41
     Tari
    0.40
     tabindex
    0.39
    वत
    0.38
    èque
    0.38
    tac
    0.38
    डीसी
    0.37
     十
    0.36
    ativ
    0.36
    ótico
    0.35
    POSITIVE LOGITS
     restrain
    0.44
     bitten
    0.41
     অংশের
    0.40
    execution
    0.38
    ស្ថាន
    0.38
    覧
    0.38
    ธ์
    0.38
     Contain
    0.37
     executed
    0.37
    iaxial
    0.37
    Activations Density 0.002%

    No Known Activations