© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 62998
    Prev
    Next
    INDEX
    Explanations

    batting/hitting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lifted
    0.41
    ఆర్
    0.41
     pro
    0.39
     Archive
    0.38
     Parker
    0.38
    誢
    0.38
     Mar
    0.37
    タク
    0.36
     parker
    0.35
    앰
    0.35
    POSITIVE LOGITS
     knock
    0.49
    BAT
    0.47
     knocking
    0.46
     batting
    0.46
     Knock
    0.45
     knocks
    0.45
    kernels
    0.45
    bat
    0.43
    bo
    0.41
     boot
    0.40
    Activations Density 0.004%

    No Known Activations