© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 197300
    Prev
    Next
    INDEX
    Explanations

    list or numerical sequence

    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_26_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
    us
    0.30
    ę
    0.30
     இருந்து
    0.28
    u
    0.28
     thorn
    0.28
    ).
    0.27
     up
    0.27
     or
    0.26
     peaks
    0.26
     පිට
    0.26
    POSITIVE LOGITS
    ꫝ
    0.34
    ९
    0.32
    ۹
    0.31
    ofType
    0.28
    וט
    0.28
    ethylsulfanyl
    0.28
     Feynman
    0.27
     Scienze
    0.27
     bialgebras
    0.27
    יות
    0.27
    Activations Density 0.002%

    No Known Activations