© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236850
    Prev
    Next
    INDEX
    Explanations

    for loops

    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_25_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
     taut
    0.28
     “
    0.27
    為
    0.27
     determine
    0.26
     graceful
    0.25
     depending
    0.24
     determined
    0.24
    .(
    0.24
     appropriately
    0.24
     proportional
    0.24
    POSITIVE LOGITS
    িত্তিক
    0.28
    苃
    0.28
    ကား
    0.27
     Stamps
    0.25
    خاص
    0.25
    ertools
    0.25
    鸢
    0.24
    unki
    0.24
    ১২শ
    0.24
    ினம்
    0.24
    Activations Density 0.001%

    No Known Activations