© 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. 11421
    Prev
    Next
    INDEX
    Explanations

    calculations and explanations

    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
    sdag
    0.40
    安
    0.40
     মানুষদের
    0.37
     लोकांनी
    0.37
     melap
    0.37
    犬
    0.36
     Clique
    0.36
    Traversal
    0.36
    Ad
    0.36
    गीय
    0.35
    POSITIVE LOGITS
     raised
    0.42
    FromNib
    0.38
    raised
    0.38
    риста
    0.38
     गों
    0.38
     numeracy
    0.37
    juana
    0.37
     raising
    0.37
    ++',
    0.37
     ஒன்று
    0.36
    Activations Density 0.018%

    No Known Activations