© 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. 167514
    Prev
    Next
    INDEX
    Explanations

    if statements in code

    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
    omal
    0.31
    isso
    0.31
     அறு
    0.30
    urgery
    0.30
    োয়ার
    0.30
     자
    0.29
    adn
    0.29
    izzando
    0.29
    annulation
    0.29
     कैरेट
    0.28
    POSITIVE LOGITS
     Kr
    0.35
     buscador
    0.34
     saludo
    0.31
    Kr
    0.30
    挨拶
    0.30
    弃
    0.30
     Gallen
    0.30
    进去
    0.30
     অগ্নি
    0.30
    里面的
    0.30
    Activations Density 0.000%

    No Known Activations