© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14119
    Prev
    Next
    INDEX
    Explanations

    medal count and podium finishes

    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_13_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
    uh
    0.53
    不大
    0.44
    affirming
    0.42
     الايه
    0.41
    Bat
    0.41
     независи
    0.40
    â
    0.40
    Pick
    0.40
     पिक
    0.40
    ult
    0.39
    POSITIVE LOGITS
     medal
    0.54
     medals
    0.50
     oluyor
    0.48
     Security
    0.47
     grenade
    0.46
     LE
    0.45
     Laplacian
    0.45
    ୩
    0.45
     Manufacturing
    0.45
    侨
    0.44
    Activations Density 0.004%

    No Known Activations