© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208548
    Prev
    Next
    INDEX
    Explanations

    confidence interval

    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_20_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
     同じ
    0.47
     θ
    0.45
    費用
    0.44
     ω
    0.43
     원래
    0.43
     :::
    0.43
     radius
    0.42
     radial
    0.42
     γ
    0.42
     PackageManager
    0.42
    POSITIVE LOGITS
    מים
    0.47
    öglichkeiten
    0.47
    örungen
    0.46
    áreas
    0.43
    كثر
    0.42
    awatan
    0.42
    equilib
    0.42
    STRU
    0.42
    enciais
    0.41
    grown
    0.41
    Activations Density 0.000%

    No Known Activations