© 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. 179679
    Prev
    Next
    INDEX
    Explanations

    those

    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
    $=\
    0.39
     $=\
    0.39
    TED
    0.37
    candy
    0.37
    ingt
    0.37
    രണം
    0.36
    kyt
    0.36
    ching
    0.35
     artillery
    0.35
    ">=</
    0.35
    POSITIVE LOGITS
     hose
    0.63
     thoe
    0.63
     those
    0.60
    those
    0.58
     Thos
    0.57
     tho
    0.55
     th
    0.53
     aquellos
    0.52
    hose
    0.52
     aque
    0.50
    Activations Density 0.003%

    No Known Activations