© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21644
    Prev
    Next
    INDEX
    Explanations

    G

    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_56_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
    amento
    0.38
    İR
    0.37
    Ons
    0.37
     fucked
    0.36
    fuck
    0.36
    襖
    0.36
     Sailors
    0.36
    pekt
    0.35
    nR
    0.34
    瑗
    0.34
    POSITIVE LOGITS
    川
    0.40
     যশ
    0.37
     azo
    0.37
    Sentiment
    0.37
     川
    0.35
    oute
    0.35
    umbia
    0.35
    ເອ
    0.34
    filed
    0.34
    CORD
    0.34
    Activations Density 0.008%

    No Known Activations