© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32891
    Prev
    Next
    INDEX
    Explanations

    concepts and terms

    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_50_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
    رحبا
    0.42
     Praise
    0.39
    arean
    0.38
     stipulated
    0.36
    ાર
    0.36
     bon
    0.35
     वेगवेग
    0.35
    
    0.34
    Shift
    0.34
    нимание
    0.34
    POSITIVE LOGITS
     articulated
    0.44
     progett
    0.44
    zta
    0.43
     organic
    0.42
    zia
    0.41
    continuity
    0.40
     articul
    0.40
    alta
    0.39
    Organic
    0.39
    olah
    0.39
    Activations Density 0.010%

    No Known Activations