© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9422
    Prev
    Next
    INDEX
    Explanations

    origin and formation

    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_13_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
    разу
    0.37
     conjugated
    0.35
    拯
    0.35
     Enzymes
    0.34
     terão
    0.34
    норий
    0.33
    ણે
    0.33
    增加了
    0.33
    棪
    0.33
     consecutively
    0.32
    POSITIVE LOGITS
    o
    0.41
    cs
    0.38
    ng
    0.36
    v
    0.36
    asters
    0.35
     cared
    0.35
    evolution
    0.35
    olem
    0.34
     origins
    0.34
     "")
    0.34
    Activations Density 0.100%

    No Known Activations