© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11989
    Prev
    Next
    INDEX
    Explanations

    shaft and load configurations

    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_13_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
    ף
    0.52
     rafts
    0.47
     fromage
    0.45
     ES
    0.44
    尔
    0.44
    isés
    0.43
    LogRow
    0.43
    ERTS
    0.43
     trays
    0.42
     navigation
    0.41
    POSITIVE LOGITS
     meskipun
    0.51
     Meskipun
    0.51
    "),
    0.50
    springframework
    0.49
    \%),
    0.49
     Adjustable
    0.49
     wèi
    0.47
    ការពារ
    0.47
     Alarm
    0.47
    losen
    0.47
    Activations Density 0.002%

    No Known Activations