© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51257
    Prev
    Next
    INDEX
    Explanations

    UI elements

    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_55_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
     تحقق
    0.41
     geprüft
    0.39
     FileReader
    0.37
    viewer
    0.37
    টা
    0.37
    টাকে
    0.37
    崠
    0.37
    之下
    0.36
     spit
    0.36
     interpretations
    0.36
    POSITIVE LOGITS
     navigational
    0.43
     बाएं
    0.42
    filtering
    0.41
     filtering
    0.41
     left
    0.40
    deals
    0.39
     promi
    0.39
    clearly
    0.38
     izquierda
    0.38
     links
    0.37
    Activations Density 0.008%

    No Known Activations