© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162069
    Prev
    Next
    INDEX
    Explanations

    audit trails and logs

    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
    稽
    0.36
     WIT
    0.36
     കമ്മി
    0.34
    ulpt
    0.33
     rapporter
    0.33
     пос
    0.33
    куль
    0.32
     指
    0.32
     скры
    0.32
    近代
    0.32
    POSITIVE LOGITS
     Disposal
    0.33
     sand
    0.32
    ('*
    0.32
     夕
    0.32
     मक्
    0.32
    Aqua
    0.32
    Rock
    0.31
     ವಿಶೇಷ
    0.30
     mas
    0.30
     पूर्वा
    0.30
    Activations Density 0.005%

    No Known Activations