© 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. 120729
    Prev
    Next
    INDEX
    Explanations

    operator precedence

    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
    össä
    0.41
    ਗੇ
    0.40
    ல்ல
    0.39
     debunk
    0.38
    Cory
    0.37
    ›
    0.37
     Valley
    0.37
     xyl
    0.37
    谴
    0.36
     Cory
    0.36
    POSITIVE LOGITS
     urgent
    0.49
     immediate
    0.46
     insistent
    0.44
     urgency
    0.44
    immediate
    0.43
     dringend
    0.41
     IComparable
    0.39
    واب
    0.38
     postponement
    0.38
     प्रतिद्व
    0.37
    Activations Density 0.002%

    No Known Activations