© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176422
    Prev
    Next
    INDEX
    Explanations

    Explaining sections or concepts

    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_20_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
    Nur
    0.52
     NUR
    0.49
     Nur
    0.43
    坐标
    0.42
    泫
    0.40
    滸
    0.39
    Assistant
    0.39
    記得
    0.39
    squares
    0.39
    stethoscope
    0.39
    POSITIVE LOGITS
     Además
    0.53
     Cependant
    0.46
     ಆದರೆ
    0.46
     પરંતુ
    0.45
     (−
    0.45
     देखील
    0.44
     માટે
    0.44
    folio
    0.43
     हानिकारक
    0.41
    (−
    0.41
    Activations Density 0.003%

    No Known Activations