© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31665
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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_50_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
     integers
    0.38
     জাক
    0.36
    тился
    0.35
    ?')
    0.35
    fia
    0.35
    inha
    0.34
    逶
    0.34
    conta
    0.33
    äv
    0.33
     NT
    0.32
    POSITIVE LOGITS
    MoveNext
    0.38
    十大
    0.38
     الاقوامی
    0.37
     ===========
    0.36
     kerat
    0.36
    ffield
    0.36
     کہ
    0.35
    ﻼ
    0.35
    España
    0.35
    Microelectronics
    0.35
    Activations Density 0.021%

    No Known Activations