© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149519
    Prev
    Next
    INDEX
    Explanations

    circuits connected in series

    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_23_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
    Mixin
    0.42
    =[]
    0.40
    以后
    0.40
    Nec
    0.39
    Callback
    0.37
     Nec
    0.37
     =
    0.37
     gue
    0.36
    kep
    0.36
     제외
    0.36
    POSITIVE LOGITS
    城堡
    0.42
     WED
    0.42
     дет
    0.41
    靼
    0.40
     Dickens
    0.40
     Transient
    0.40
     ट्रायंगल
    0.39
     шта
    0.39
    tbLabel
    0.39
    ге
    0.39
    Activations Density 0.001%

    No Known Activations