© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64451
    Prev
    Next
    INDEX
    Explanations

    bunt | sacrifice | buntting

    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_41_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
     shots
    0.50
     Shots
    0.45
     hitting
    0.41
     hitter
    0.40
    柱
    0.40
     स्म
    0.39
     hitters
    0.38
    Hit
    0.37
    shots
    0.37
    Dock
    0.37
    POSITIVE LOGITS
     bunt
    0.59
     Sacrifice
    0.46
     bun
    0.46
     bum
    0.46
     번
    0.45
    bundle
    0.43
     sacrificed
    0.42
    번
    0.41
     sacrifice
    0.41
     COE
    0.41
    Activations Density 0.001%

    No Known Activations