© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 2200
    Prev
    Next
    INDEX
    Explanations

    Hulk smash

    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
     ofApp
    0.38
    Comma
    0.38
    柄
    0.37
     Knight
    0.37
    之家
    0.37
     приме
    0.37
    mechanical
    0.36
    庠
    0.36
     colony
    0.36
    lor
    0.35
    POSITIVE LOGITS
     hulk
    1.30
     Hulk
    1.20
     hul
    1.18
     Hul
    1.14
    hul
    0.91
     smash
    0.82
     gamma
    0.75
     smashed
    0.70
     hulls
    0.69
     Incredible
    0.68
    Activations Density 0.023%

    No Known Activations