© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232552
    Prev
    Next
    INDEX
    Explanations

    Google

    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
    ẩu
    0.36
     nitidus
    0.36
     nCurrent
    0.36
     serm
    0.36
     कोटी
    0.35
    decompose
    0.35
    Tissue
    0.35
    币
    0.35
     vent
    0.34
     desigualdad
    0.34
    POSITIVE LOGITS
     Cloud
    0.46
    Cloud
    0.42
     Reporting
    0.41
    debugging
    0.40
    uter
    0.39
    udir
    0.38
     reporting
    0.38
     Wikidata
    0.38
    redit
    0.37
    MySQL
    0.37
    Activations Density 0.002%

    No Known Activations