© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30434
    Prev
    Next
    INDEX
    Explanations

    stiff or Eng

    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
    ordelen
    0.45
    ysł
    0.41
     fato
    0.39
    Tray
    0.37
     thorn
    0.37
     ሜ
    0.37
     tray
    0.36
    筍
    0.36
    ovsky
    0.35
    酪
    0.35
    POSITIVE LOGITS
    azer
    0.38
     transform
    0.37
     Luther
    0.37
     आधी
    0.36
     eng
    0.36
    Eng
    0.35
     అలీ
    0.35
     Республи
    0.35
     stiff
    0.35
     Hitch
    0.34
    Activations Density 0.047%

    No Known Activations