© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 166864
    Prev
    Next
    INDEX
    Explanations

    pneumothorax

    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
     پت
    0.38
     actions
    0.36
    p
    0.36
    াতে
    0.36
     self
    0.35
     overwhelming
    0.35
    plas
    0.35
    ACTIONS
    0.34
     shrinking
    0.34
     pâ
    0.34
    POSITIVE LOGITS
    shoulder
    0.48
    肩膀
    0.48
     कंधे
    0.47
    ો
    0.46
     肩
    0.45
    肩
    0.44
    othor
    0.44
     chest
    0.42
     épaules
    0.42
     shoulder
    0.42
    Activations Density 0.001%

    No Known Activations