© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32130
    Prev
    Next
    INDEX
    Explanations

    Quarter-finals, finals, second rounds

    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
     paints
    0.37
     Killing
    0.37
    Killing
    0.37
     asalamualaikum
    0.36
    টক
    0.36
    滅
    0.35
     dod
    0.35
    ️
    0.35
     protestors
    0.34
    icke
    0.34
    POSITIVE LOGITS
     leg
    1.08
    legs
    1.05
     legs
    1.02
    leg
    0.97
    Leg
    0.94
     Leg
    0.91
    腿
    0.91
     Legs
    0.86
    legged
    0.82
     legg
    0.76
    Activations Density 0.001%

    No Known Activations