© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11043
    Prev
    Next
    INDEX
    Explanations

    #4CAF50

    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_40_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
    expose
    0.40
    systems
    0.39
     analyt
    0.39
    ystems
    0.39
     pertenece
    0.38
    asche
    0.38
    ১২
    0.38
    ֱ
    0.38
     tweak
    0.37
     impeach
    0.37
    POSITIVE LOGITS
     Gus
    0.39
    脂肪
    0.39
    با
    0.38
    burgh
    0.37
    ้อ
    0.36
    setMin
    0.36
    妞
    0.36
     맥
    0.35
    бая
    0.35
     Ausstattung
    0.35
    Activations Density 0.001%

    No Known Activations