© 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. 199215
    Prev
    Next
    INDEX
    Explanations

    word parts

    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
     grand
    0.40
    াত্র
    0.40
    எல்
    0.38
    POs
    0.38
    QL
    0.37
    <0xAC>
    0.37
    grand
    0.36
    भि
    0.36
    ত্র
    0.35
     bilayers
    0.35
    POSITIVE LOGITS
     Tan
    0.44
    atan
    0.44
    ule
    0.44
     tan
    0.42
    Tan
    0.39
    疣
    0.39
    alan
    0.38
    atee
    0.38
    GIN
    0.38
    म्मा
    0.38
    Activations Density 0.007%

    No Known Activations