© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22067
    Prev
    Next
    INDEX
    Explanations

    body parts and sensations

    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_56_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
    腹
    1.90
     abdominal
    1.82
     belly
    1.78
     Belly
    1.71
     abdomen
    1.57
    belly
    1.57
    abdominal
    1.52
     abdom
    1.51
     abdomin
    1.42
     bụng
    1.41
    POSITIVE LOGITS
    お
    0.48
    釧
    0.42
     Cayman
    0.39
     Jac
    0.39
     dist
    0.38
    觀塘
    0.36
    ایی
    0.36
     cristian
    0.36
     Boise
    0.35
     Ketch
    0.35
    Activations Density 0.029%

    No Known Activations