© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216590
    Prev
    Next
    INDEX
    Explanations

    small positive descriptions

    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_47_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
    elling
    0.38
     descargar
    0.38
     délé
    0.37
    antos
    0.36
     psa
    0.36
     MMA
    0.35
    ০১
    0.35
     ჯ
    0.34
    관
    0.34
     bargain
    0.34
    POSITIVE LOGITS
     tiny
    0.49
     beautifully
    0.49
     funny
    0.48
    ন্যার
    0.45
    funny
    0.44
     সুন্দর
    0.43
     lovingly
    0.43
     minuscule
    0.43
    tiny
    0.43
     малень
    0.42
    Activations Density 0.000%

    No Known Activations