© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200838
    Prev
    Next
    INDEX
    Explanations

    names

    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_50_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
     Traffic
    0.41
     G
    0.40
    PD
    0.40
    Sticky
    0.39
     Sticky
    0.39
    श्य
    0.38
     Paul
    0.38
     Stump
    0.38
    traffic
    0.37
     Flood
    0.37
    POSITIVE LOGITS
     quinqu
    0.45
     DOM
    0.42
     پانچ
    0.41
     peonies
    0.40
    浴室
    0.38
     Tanganyika
    0.38
    挽
    0.38
    극한
    0.38
     thermodynam
    0.36
     avocados
    0.36
    Activations Density 0.030%

    No Known Activations