© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208036
    Prev
    Next
    INDEX
    Explanations

    bowel movements

    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_20_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
     breakthroughs
    0.42
     výro
    0.41
     támogat
    0.41
     essentials
    0.40
     కారణంగా
    0.40
    tuples
    0.39
    ╩
    0.39
    assadors
    0.39
     sínt
    0.38
    agements
    0.38
    POSITIVE LOGITS
     einer
    0.47
    ας
    0.46
    ⓑ
    0.42
     overgrown
    0.40
     Border
    0.39
     Zuck
    0.38
    茵
    0.37
    Border
    0.37
    стон
    0.37
     eingef
    0.37
    Activations Density 0.002%

    No Known Activations