© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140262
    Prev
    Next
    INDEX
    Explanations

    Travis Scott, Cactus Jack, Rodeo Drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     Nazionale
    0.58
    ire
    0.50
    झ्
    0.50
    otas
    0.49
    琵
    0.48
    GameState
    0.48
     Kwiatkowski
    0.48
     Dresses
    0.48
     உண்மை
    0.47
    ena
    0.46
    POSITIVE LOGITS
     jude
    0.61
     трёх
    0.58
     globalization
    0.57
     crowd
    0.55
    Globalization
    0.54
     Jude
    0.54
     jud
    0.53
     col
    0.53
     пут
    0.53
     壁
    0.52
    Activations Density 0.000%

    No Known Activations