© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181281
    Prev
    Next
    INDEX
    Explanations

    add ingredients or variations

    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_29_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
     belleza
    0.39
    সজ্জিত
    0.39
    ாலே
    0.38
     tasar
    0.37
     segala
    0.37
     intensa
    0.37
    激
    0.37
    辇
    0.37
     tas
    0.36
    现代
    0.36
    POSITIVE LOGITS
     slightly
    0.39
    either
    0.38
     either
    0.38
     थोड़ा
    0.38
    slightly
    0.38
     Slightly
    0.37
    하거나
    0.37
     কিংবা
    0.37
    Nearby
    0.37
    rgba
    0.36
    Activations Density 0.006%

    No Known Activations