© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180563
    Prev
    Next
    INDEX
    Explanations

    calibrated, resetting, located, convergence

    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_24_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
    BITMAP
    0.47
     وقتی
    0.46
     ఆల
    0.46
    nummer
    0.46
    JVM
    0.46
    algèbre
    0.45
    attice
    0.44
    棻
    0.44
    Computation
    0.43
     PTSD
    0.42
    POSITIVE LOGITS
    iye
    0.52
    не
    0.48
    ции
    0.47
    ной
    0.46
     deliver
    0.46
    လီ
    0.46
     ಇದನ್ನು
    0.46
     giỏi
    0.45
    ように
    0.44
     Gub
    0.44
    Activations Density 0.000%

    No Known Activations