© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66670
    Prev
    Next
    INDEX
    Explanations

    bh sound

    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_51_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
    wärm
    0.41
    HEMAT
    0.41
     रे
    0.39
    रे
    0.39
    ziná
    0.38
     rosy
    0.38
    rech
    0.38
    ⋮
    0.38
    력
    0.38
    warming
    0.37
    POSITIVE LOGITS
     bh
    0.77
     bho
    0.73
     Bho
    0.70
     BH
    0.69
     भ
    0.69
    bh
    0.66
    भो
    0.64
     Bh
    0.64
    Bh
    0.61
    bog
    0.61
    Activations Density 0.000%

    No Known Activations