© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 215539
    Prev
    Next
    INDEX
    Explanations

    Technical and commercial terms

    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_47_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
     Lod
    0.50
     McLean
    0.47
     niacin
    0.45
    朗
    0.44
     niv
    0.43
     RE
    0.42
     lodging
    0.42
     Historic
    0.42
     refuge
    0.41
     Ł
    0.41
    POSITIVE LOGITS
    anta
    0.37
    icule
    0.37
    zmdi
    0.37
    entropy
    0.36
    Products
    0.35
     Sü
    0.35
     chairmanship
    0.34
    Doom
    0.34
    Trendy
    0.34
    xml
    0.33
    Activations Density 0.005%

    No Known Activations