© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124140
    Prev
    Next
    INDEX
    Explanations

    water table

    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_3_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
    πτυ
    0.76
    다
    0.75
    gı
    0.71
    де
    0.70
    gru
    0.68
     객
    0.67
    ३
    0.66
    𝘃
    0.66
    pture
    0.66
    ડ
    0.64
    POSITIVE LOGITS
     WATER
    0.81
    น
    0.73
     Water
    0.67
     vody
    0.66
     Yorker
    0.66
    ีย
    0.64
     Hessian
    0.64
     INST
    0.63
    0.63
     தண்ணீர்
    0.62
    Activations Density 0.002%

    No Known Activations