© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134140
    Prev
    Next
    INDEX
    Explanations

    Benefits of

    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_37_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
    benzoimidazol
    0.42
     શરી
    0.39
     သည်
    0.36
    
    0.35
    বুব
    0.35
    ුව
    0.35
     purported
    0.34
     പ്രത്യ
    0.34
    ](
    0.34
    袁
    0.34
    POSITIVE LOGITS
     Nuss
    0.41
     nutshell
    0.39
    Compared
    0.39
    由
    0.37
     Karriere
    0.36
     Weddings
    0.36
     costituito
    0.36
     Compared
    0.35
    fern
    0.35
     '/':
    0.35
    Activations Density 0.006%

    No Known Activations