© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239146
    Prev
    Next
    INDEX
    Explanations

    __init__ or __str__ methods

    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_25_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
     Toxicology
    0.39
    totalSupply
    0.38
     Facility
    0.38
    enem
    0.36
    ๕
    0.36
     Therapeutics
    0.36
    Facility
    0.35
    ociety
    0.35
     pity
    0.35
     Doctorate
    0.34
    POSITIVE LOGITS
    lassen
    0.43
    withtag
    0.42
    樑
    0.39
    ခံ
    0.39
     membuat
    0.39
    ashing
    0.39
     Aussch
    0.38
    
    0.38
    ഞ്ച
    0.37
     modellen
    0.37
    Activations Density 0.000%

    No Known Activations