© 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. 76953
    Prev
    Next
    INDEX
    Explanations

    aspect of life

    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
    謠
    0.41
     erroneously
    0.38
     approximated
    0.36
    Pope
    0.36
     சீன
    0.31
     inaccur
    0.31
     मिल्
    0.31
    izations
    0.31
     approximate
    0.30
     দেয়
    0.30
    POSITIVE LOGITS
     HP
    0.34
     sla
    0.31
     NIC
    0.31
    ῷ
    0.31
     LIFE
    0.30
     caste
    0.30
     пару
    0.30
     confort
    0.29
    ckt
    0.29
     HSE
    0.29
    Activations Density 0.004%

    No Known Activations