© 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. 198383
    Prev
    Next
    INDEX
    Explanations

    end

    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
    ⠀
    0.41
     নজরুল
    0.38
     baseApiPath
    0.38
    ekan
    0.37
    பை
    0.37
    వన్
    0.37
    全
    0.37
    ⠀⠀
    0.37
    மார்
    0.36
     acorn
    0.36
    POSITIVE LOGITS
    ǒ
    0.41
     some
    0.40
     några
    0.39
    两侧
    0.39
    ый
    0.37
     nogle
    0.37
     Teil
    0.36
     část
    0.36
     &&
    0.36
    ம்ப
    0.35
    Activations Density 0.001%

    No Known Activations