© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84499
    Prev
    Next
    INDEX
    Explanations

    internet culture and slang

    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_0_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
    s
    1.66
    stown
    1.55
    ل
    1.55
    n
    1.54
    ni
    1.52
    land
    1.48
    ↵
    1.45
     the
    1.40
    л
    1.27
    ne
    1.25
    POSITIVE LOGITS
    ０
    2.25
    0
    2.06
    𝟬
    1.94
    
    1.78
    ۰۰
    1.66
     ০
    1.61
     departamentos
    1.61
    ۰
    1.61
    ၀
    1.61
    𝟎
    1.60
    Activations Density 0.001%

    No Known Activations