© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115567
    Prev
    Next
    INDEX
    Explanations

    avoid anything

    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_27_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
     Surveys
    0.38
     abstracted
    0.37
     الاشكال
    0.35
    ogat
    0.35
     оди
    0.35
    株式
    0.34
     elicited
    0.34
     ):
    0.34
     .:
    0.34
     compensated
    0.33
    POSITIVE LOGITS
    setTo
    0.38
    }^{-\
    0.37
    ຽງ
    0.37
    ίζουν
    0.37
    ίζει
    0.36
    Truman
    0.36
     walkway
    0.36
    ברי
    0.35
    َرْ
    0.35
     பட்
    0.35
    Activations Density 0.004%

    No Known Activations