© 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. 219918
    Prev
    Next
    INDEX
    Explanations

    difficult to do

    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
     തൊ
    0.30
     Velocity
    0.29
    ऐसे
    0.29
     Reload
    0.29
     recalcul
    0.29
     फास्ट
    0.28
    Sho
    0.28
    埛
    0.28
    重生
    0.28
    aiser
    0.27
    POSITIVE LOGITS
     nt
    0.32
    হাওয়া
    0.30
     Sardegna
    0.28
     Tuscany
    0.27
     passi
    0.27
     skepticism
    0.27
    はなく
    0.27
     رع
    0.26
     wa
    0.26
     ছুটি
    0.26
    Activations Density 0.011%

    No Known Activations