© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5880
    Prev
    Next
    INDEX
    Explanations

    Snake game

    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_39_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
    ScrollPane
    0.42
     закончи
    0.41
     라는
    0.41
    गोरि
    0.40
     predominate
    0.40
     দেখিলাম
    0.39
    प्रधान
    0.38
    轆
    0.38
     purchaser
    0.38
     organizz
    0.38
    POSITIVE LOGITS
     finely
    0.38
     πο
    0.37
    egg
    0.37
    Thanks
    0.36
      
    0.35
     Mo
    0.35
    PIN
    0.35
    Rest
    0.35
     mày
    0.35
     thanks
    0.34
    Activations Density 0.011%

    No Known Activations