© 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. 159054
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     monoc
    0.38
    IList
    0.37
     Hansen
    0.36
    klik
    0.36
    lemish
    0.34
     IList
    0.33
     Hurts
    0.33
    䊀
    0.33
     Hanna
    0.33
     kompos
    0.33
    POSITIVE LOGITS
    header
    0.61
    headers
    0.60
     header
    0.55
     headers
    0.54
    Header
    0.54
     заго
    0.52
     ヘ
    0.51
     Header
    0.49
     Agent
    0.49
    ヘ
    0.48
    Activations Density 0.002%

    No Known Activations