© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16884
    Prev
    Next
    INDEX
    Explanations

    html break tag `<br>`

    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_40_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
    
    0.40
    quirrel
    0.38
    ('');
    0.37
    ();//
    0.37
    ('/');
    0.37
     destruct
    0.37
     ahli
    0.37
     sections
    0.36
     skon
    0.35
    👠
    0.35
    POSITIVE LOGITS
     Swe
    0.42
    лизации
    0.38
    标签
    0.37
    tags
    0.37
     Brice
    0.35
    Tag
    0.35
    Tags
    0.35
    Swe
    0.35
     Sweep
    0.35
     Hendrick
    0.35
    Activations Density 0.002%

    No Known Activations