© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58904
    Prev
    Next
    INDEX
    Explanations

    blood clotting aggregation hemolysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
     gebru
    0.52
    etre
    0.48
     miner
    0.48
     eb
    0.47
     oid
    0.47
     nine
    0.47
     cost
    0.46
    e
    0.46
     harming
    0.46
     ihres
    0.46
    POSITIVE LOGITS
    리가
    0.58
    DUNLAND
    0.58
    Budget
    0.57
    BC
    0.56
    CC
    0.55
    Basic
    0.54
    Psych
    0.54
     Philosoph
    0.54
    Workshop
    0.54
    Humans
    0.54
    Activations Density 0.023%

    No Known Activations