© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131177
    Prev
    Next
    INDEX
    Explanations

    talent

    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
    侏
    0.39
    Meth
    0.38
     испо
    0.38
     denomina
    0.37
     vase
    0.37
    $">
    0.37
     দায়
    0.36
    旗
    0.36
    ės
    0.35
     mehrerer
    0.35
    POSITIVE LOGITS
    Tal
    3.03
     Tal
    2.91
     tal
    2.89
     Talent
    2.48
    tal
    2.44
     TAL
    2.41
     talent
    2.36
    TAL
    2.31
    talent
    2.22
     talents
    2.13
    Activations Density 0.008%

    No Known Activations