© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3100
    Prev
    Next
    INDEX
    Explanations

    club, trust, membership, seals, hub

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     whistling
    0.38
     whistle
    0.38
    š
    0.36
     Summers
    0.35
     急
    0.34
     traditional
    0.34
    Gener
    0.34
     Knight
    0.34
     antis
    0.33
    ریٹر
    0.33
    POSITIVE LOGITS
    gern
    0.39
     nouns
    0.37
     दीजिएगा
    0.36
    otesi
    0.35
     रघु
    0.35
     merchandise
    0.35
     Internacional
    0.34
    讪
    0.34
    логі
    0.34
    多人
    0.34
    Activations Density 0.102%

    No Known Activations