© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215109
    Prev
    Next
    INDEX
    Explanations

    activation troubleshooter

    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
     mlijeka
    0.41
    iji
    0.36
     दूध
    0.36
    ℉
    0.36
    tgz
    0.36
    andinavian
    0.34
     reparation
    0.34
    刎
    0.34
     Gujar
    0.34
    institute
    0.33
    POSITIVE LOGITS
     компьютера
    0.39
    circ
    0.38
     pole
    0.37
     Bradley
    0.37
     webs
    0.36
     circus
    0.35
     carb
    0.34
     Pole
    0.34
     circuits
    0.33
     circuito
    0.33
    Activations Density 0.047%

    No Known Activations