© 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. 163742
    Prev
    Next
    INDEX
    Explanations

    caves and cave dwellings

    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
    and
    0.59
    ্কার
    0.56
    ли
    0.55
    b
    0.51
    び
    0.50
    ba
    0.50
     w
    0.48
    ded
    0.48
    ッシュ
    0.47
     politica
    0.47
    POSITIVE LOGITS
     korrekt
    0.60
     المستخدم
    0.58
     intervalles
    0.57
     accès
    0.54
    陉
    0.52
     navigateur
    0.50
     quels
    0.50
     latéral
    0.49
     neurom
    0.48
    ಟಕ
    0.48
    Activations Density 0.000%

    No Known Activations