© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183524
    Prev
    Next
    INDEX
    Explanations

    game statistics

    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
     buried
    0.41
     poorly
    0.41
     attempted
    0.37
    न्दु
    0.37
     tubules
    0.37
    ᱩ
    0.36
     inaccuracies
    0.36
     tub
    0.36
     enterr
    0.36
     døde
    0.35
    POSITIVE LOGITS
    Otros
    0.38
    traverse
    0.37
    unnumbered
    0.37
     ट्रेलर
    0.36
     Га
    0.36
    긱
    0.36
     Validator
    0.36
    AutoGen
    0.34
    فاق
    0.34
    ttf
    0.33
    Activations Density 0.000%

    No Known Activations