© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217925
    Prev
    Next
    INDEX
    Explanations

    Example:

    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_31_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
     ਕੁ
    0.42
     neutrals
    0.38
    Zhou
    0.36
    ibaldi
    0.36
    iciado
    0.35
     miserably
    0.35
     Shekhar
    0.33
    │
    0.33
    IOT
    0.33
     Zhou
    0.33
    POSITIVE LOGITS
     pertenecen
    0.41
     vectơ
    0.37
    ivam
    0.36
    тами
    0.34
    Infof
    0.33
    dafx
    0.33
     Supportive
    0.33
     конкре
    0.33
     gyn
    0.33
    bitmap
    0.32
    Activations Density 0.006%

    No Known Activations