© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42249
    Prev
    Next
    INDEX
    Explanations

    injury or illness

    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_3_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
    Ez
    0.58
    vian
    0.54
    ִי
    0.54
    ാന്‍
    0.53
    h
    0.52
     optimise
    0.52
    סטי
    0.52
    ¹.
    0.51
    ीडियो
    0.51
    િયન
    0.51
    POSITIVE LOGITS
    د
    0.86
    д
    0.72
    2
    0.64
    重建
    0.64
    ']
    0.63
     trastornos
    0.62
     And
    0.61
     Minecraft
    0.60
     investigadores
    0.60
     इंपोर्टेंट
    0.59
    Activations Density 0.003%

    No Known Activations