© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77904
    Prev
    Next
    INDEX
    Explanations

    pad

    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_53_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
     bub
    0.63
    Bub
    0.63
     B
    0.59
    bub
    0.59
     Bub
    0.57
     ben
    0.54
     Ben
    0.52
    Ben
    0.52
     Б
    0.51
     bij
    0.50
    POSITIVE LOGITS
     pad
    0.46
    Pad
    0.44
     Pad
    0.44
     Tand
    0.43
     nano
    0.42
     tandem
    0.42
    pad
    0.42
     Udaipur
    0.39
     Embr
    0.39
     saw
    0.39
    Activations Density 0.003%

    No Known Activations