© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258047
    Prev
    Next
    INDEX
    Explanations

    processes, workers, buffer, system

    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_22_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
     Artículo
    0.42
    CDF
    0.41
     Colo
    0.41
     chromosomal
    0.40
    攽
    0.40
    cesor
    0.40
    োই
    0.40
    osome
    0.39
    BNA
    0.39
     ene
    0.39
    POSITIVE LOGITS
    asserie
    0.43
    પો
    0.43
    〜
    0.43
     دسترس
    0.42
    kjhtml
    0.41
    éder
    0.41
    
    0.40
    доступ
    0.39
    蝼
    0.39
     nende
    0.39
    Activations Density 0.000%

    No Known Activations