© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63421
    Prev
    Next
    INDEX
    Explanations

    App

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     capital
    0.50
    all
    0.49
    sat
    0.44
    en
    0.43
    capital
    0.42
    成
    0.42
    x
    0.41
     sat
    0.41
     capitale
    0.40
     Sat
    0.40
    POSITIVE LOGITS
     ква
    0.39
     desvi
    0.39
    ượu
    0.38
    嬅
    0.38
     CELLS
    0.38
     cellule
    0.38
     वस्त्र
    0.37
     клетки
    0.37
     الخلا
    0.37
     valoración
    0.37
    Activations Density 0.001%

    No Known Activations