© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200523
    Prev
    Next
    INDEX
    Explanations

    assignments and definitions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Maxwell
    0.44
     $+
    0.41
    Maxwell
    0.41
     мах
    0.40
     toucher
    0.39
    Touch
    0.38
     Touch
    0.37
    notifications
    0.37
     Leslie
    0.37
    $+
    0.37
    POSITIVE LOGITS
     imagen
    0.44
     image
    0.44
    圖像
    0.41
     imagem
    0.40
    cbind
    0.40
     immagini
    0.40
     इमेज
    0.39
    localVarPath
    0.39
    သည်
    0.39
    儚
    0.38
    Activations Density 0.004%

    No Known Activations