© 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. 208810
    Prev
    Next
    INDEX
    Explanations

    Glenlivet, Sos, Blackwood Manor

    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
     पॉलिटिकल
    0.29
    िश्वत
    0.27
     Equatorial
    0.27
     nomencl
    0.26
    സ്ലാ
    0.26
    駿
    0.26
    ilibr
    0.25
     эксперимента
    0.25
    incub
    0.25
    ில்லிய
    0.25
    POSITIVE LOGITS
     म
    0.27
     M
    0.26
     მ
    0.26
    nessy
    0.26
     क
    0.26
     ম
    0.25
    )
    0.25
    테
    0.24
     साइट
    0.24
     те
    0.24
    Activations Density 0.001%

    No Known Activations