© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243858
    Prev
    Next
    INDEX
    Explanations

    game status alive

    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_40_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
    Ops
    0.38
    फ्रेंड
    0.37
     bł
    0.37
    頔
    0.37
     ছুই
    0.37
    mouseleave
    0.37
    蜇
    0.37
     ByteArray
    0.36
    髀
    0.36
    mouseout
    0.36
    POSITIVE LOGITS
     alive
    1.58
    alive
    1.35
     Alive
    1.35
    Alive
    1.25
     살아
    1.20
     जीवित
    1.19
    活着
    1.09
     जिंदा
    1.05
     জীবিত
    1.05
     surviving
    1.02
    Activations Density 0.040%

    No Known Activations