© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79073
    Prev
    Next
    INDEX
    Explanations

    potential for high returns

    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_31_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
    criptor
    0.41
     Просто
    0.40
    信頼
    0.40
    比賽
    0.40
    Running
    0.39
     る
    0.38
    ।”
    0.38
    入れ
    0.38
     ياس
    0.38
    probability
    0.37
    POSITIVE LOGITS
     wealthy
    0.44
     enjoyed
    0.43
     swelled
    0.43
     millionaire
    0.42
     benefited
    0.41
     multimillion
    0.38
     characteristics
    0.37
     dol
    0.37
     enjoys
    0.37
     swelling
    0.37
    Activations Density 0.006%

    No Known Activations