© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97527
    Prev
    Next
    INDEX
    Explanations

    index creation statements

    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_14_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
    ה
    0.67
    ،
    0.60
    ال
    0.59
    ל
    0.56
    ؟
    0.55
    ชื่อ
    0.51
    برای
    0.51
    w
    0.51
    ك
    0.51
    on
    0.50
    POSITIVE LOGITS
     infographic
    0.55
     まず
    0.55
     unmittelbar
    0.51
     MNIST
    0.49
     उद्धव
    0.48
     पंचायतों
    0.48
     Lévy
    0.47
     structuring
    0.46
     reproducing
    0.46
     Utilizing
    0.46
    Activations Density 0.001%

    No Known Activations