© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14476
    Prev
    Next
    INDEX
    Explanations

    url, query, search, file, question

    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
    舧
    0.40
     lineColorSpace
    0.38
     хоть
    0.38
     pharetra
    0.37
     आवा
    0.36
     পারবেন
    0.36
    setVelocity
    0.36
    ភាព
    0.36
    velocityY
    0.35
    })}{
    0.35
    POSITIVE LOGITS
     Strikes
    0.40
    Results
    0.39
    Guesses
    0.38
    Aux
    0.37
     المعادله
    0.37
     judíos
    0.37
    Objectives
    0.36
     autof
    0.36
    Box
    0.36
    疟
    0.36
    Activations Density 0.004%

    No Known Activations