© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43374
    Prev
    Next
    INDEX
    Explanations

    spectrum

    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_13_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
     jours
    0.19
    ée
    0.17
    bola
    0.15
     urma
    0.14
     voila
    0.14
    虾
    0.14
    bole
    0.14
    dX
    0.14
     has
    0.14
    Hay
    0.14
    POSITIVE LOGITS
    IR
    0.21
    IS
    0.19
    Y
    0.17
    储存
    0.17
     Shandong
    0.17
     интегри
    0.16
     Klinefelter
    0.16
    ِی
    0.16
     Ра
    0.16
     پاک
    0.15
    Activations Density 0.000%

    No Known Activations