© 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
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104852
    Prev
    Next
    INDEX
    Explanations

    programming types

    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_44_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
     дана
    0.38
    ⑰
    0.38
     மிகு
    0.37
    ⑮
    0.36
     Keine
    0.35
    ყოფ
    0.35
    㬹
    0.34
     keine
    0.34
     Violin
    0.34
    なの
    0.34
    POSITIVE LOGITS
     Gip
    0.42
    bble
    0.40
     ape
    0.39
    անի
    0.39
    遛
    0.38
     sur
    0.38
     ҳ
    0.37
    Bruce
    0.37
     Cib
    0.37
    win
    0.37
    Activations Density 0.001%

    No Known Activations