© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196933
    Prev
    Next
    INDEX
    Explanations

    T

    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_50_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
     Reds
    0.42
    pinned
    0.40
    Nam
    0.39
     Stoner
    0.39
    Nancy
    0.39
    Red
    0.38
     gac
    0.38
     g
    0.38
    Queries
    0.38
     reds
    0.37
    POSITIVE LOGITS
     Avi
    0.42
     Adi
    0.40
    sli
    0.40
    ကာ
    0.40
     जनता
    0.37
     سل
    0.37
    ecimiento
    0.37
    ervi
    0.36
    τας
    0.36
     AER
    0.36
    Activations Density 0.003%

    No Known Activations