© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92236
    Prev
    Next
    INDEX
    Explanations

    parent structures

    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_11_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
    ну
    0.64
    шення
    0.59
    шений
    0.58
    чение
    0.57
    ш
    0.57
    вания
    0.57
    мери
    0.57
    зы
    0.56
    зив
    0.56
    вання
    0.55
    POSITIVE LOGITS
     IComparable
    0.58
    ellig
    0.57
    ava
    0.56
    ates
    0.56
    illa
    0.55
    .]
    0.55
    annon
    0.55
    ifed
    0.54
     factors
    0.53
     O
    0.53
    Activations Density 0.000%

    No Known Activations