© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58542
    Prev
    Next
    INDEX
    Explanations

    variables and expressions

    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
     cannons
    0.73
     cybers
    0.57
     frase
    0.55
    жено
    0.55
     islands
    0.54
     DRN
    0.53
     genet
    0.52
    ៊
    0.52
     grond
    0.50
     builtin
    0.50
    POSITIVE LOGITS
    am
    0.64
    would
    0.61
    ระหว่าง
    0.54
    allows
    0.52
    س
    0.52
    পূ
    0.52
    ≤
    0.52
     będą
    0.50
    ﾀ
    0.50
    at
    0.50
    Activations Density 0.005%

    No Known Activations