© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147955
    Prev
    Next
    INDEX
    Explanations

    bat

    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_59_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
     b
    3.47
     ب
    2.45
     ब
    2.36
     б
    2.34
    <0x99>
    2.19
     ব
    2.17
    บ
    2.05
    b
    1.98
     B
    1.76
     ב
    1.63
    POSITIVE LOGITS
     bat
    0.75
     Bat
    0.74
    Bat
    0.73
    bat
    0.71
    BAT
    0.57
     batang
    0.55
     BAT
    0.54
    batter
    0.51
    abat
    0.48
     بات
    0.47
    Activations Density 0.005%

    No Known Activations