© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5173
    Prev
    Next
    INDEX
    Explanations

    baseball and hockey statistics

    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_39_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
     speakers
    0.41
     McQu
    0.40
    겉
    0.40
     portes
    0.39
     antisemit
    0.39
     bouts
    0.39
    odal
    0.38
    bout
    0.38
     Ủ
    0.38
     porta
    0.37
    POSITIVE LOGITS
    Penn
    0.39
    Baseball
    0.39
     blo
    0.38
    Phill
    0.38
    Hockey
    0.37
    Valentines
    0.37
    Polynomial
    0.37
    HexString
    0.37
    사업
    0.36
    Frontend
    0.36
    Activations Density 0.002%

    No Known Activations