© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219650
    Prev
    Next
    INDEX
    Explanations

    Thrust SSC, Mad Max, MythBusters, experimental vehicles

    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_31_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
     littérature
    0.37
     लहंगा
    0.36
     flapping
    0.35
    ối
    0.33
     distracted
    0.33
    锣
    0.33
     Lite
    0.33
    omerase
    0.32
    "%>
    0.32
     distracting
    0.32
    POSITIVE LOGITS
     Kach
    0.36
     plán
    0.34
    trials
    0.34
    オク
    0.33
    Attempts
    0.32
    finement
    0.32
     बै
    0.32
     கிட்ட
    0.32
     lay
    0.32
    وضع
    0.32
    Activations Density 0.023%

    No Known Activations