© 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. 33047
    Prev
    Next
    INDEX
    Explanations

    licking

    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
    ကုန်
    0.39
     {}\
    0.36
     godina
    0.36
     cleft
    0.35
     الدنيا
    0.35
    -(\
    0.35
     getMenuInflater
    0.35
    ګه
    0.35
    /(:
    0.34
     jaren
    0.34
    POSITIVE LOGITS
    typen
    0.44
    pus
    0.39
     Struggles
    0.37
    licking
    0.37
    slack
    0.37
    sce
    0.36
    acate
    0.35
    tten
    0.35
    sack
    0.35
    lick
    0.35
    Activations Density 0.792%

    No Known Activations