© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133500
    Prev
    Next
    INDEX
    Explanations

    pulse

    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_50_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
    ียบ
    0.45
     धर
    0.42
    อร์
    0.42
    糬
    0.40
    বর
    0.39
     convict
    0.38
    争取
    0.38
    Conv
    0.38
    忍不住
    0.37
     συμπ
    0.37
    POSITIVE LOGITS
     Puls
    0.47
    Pulse
    0.44
    ó
    0.43
     pulse
    0.43
     Pulse
    0.42
     PUL
    0.41
     pulsing
    0.40
     puls
    0.40
     pulses
    0.40
     pulsed
    0.40
    Activations Density 0.002%

    No Known Activations