© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90011
    Prev
    Next
    INDEX
    Explanations

    dragoon, drag force, drag on

    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_3_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
    diği
    0.65
     cả
    0.57
     tenía
    0.57
    ❿
    0.56
     đa
    0.56
     necessità
    0.56
     بانک
    0.56
    ේ
    0.55
    discovery
    0.54
    ahuan
    0.54
    POSITIVE LOGITS
    ang
    0.70
    0
    0.68
    (
    0.65
     is
    0.64
     Drag
    0.63
     .
    0.57
    n
    0.56
     Dragon
    0.56
     .(
    0.56
     Dragons
    0.55
    Activations Density 0.001%

    No Known Activations