© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168112
    Prev
    Next
    INDEX
    Explanations

    describing places and things

    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_56_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
     (!
    0.39
     '-'
    0.38
     "-"
    0.37
     little
    0.36
     frequent
    0.35
    끽
    0.35
     sounded
    0.35
     पुरालेखित
    0.35
     powdered
    0.34
    感じです
    0.34
    POSITIVE LOGITS
    庻
    0.37
     Isolated
    0.35
    schaft
    0.34
    Yield
    0.34
    Premium
    0.34
    Medium
    0.34
    Metric
    0.34
    ولا
    0.34
    Watt
    0.34
     Coming
    0.33
    Activations Density 0.015%

    No Known Activations