© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4639
    Prev
    Next
    INDEX
    Explanations

    describing things as bold

    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
     вос
    0.39
    ady
    0.37
     製造
    0.37
     squiggle
    0.36
    obie
    0.36
    뤼
    0.36
     anisotropic
    0.35
    Khokhlov
    0.35
    enumValues
    0.35
    ADY
    0.35
    POSITIVE LOGITS
     bravely
    0.41
    项目
    0.40
    kich
    0.38
    ONENTS
    0.38
    endes
    0.36
    탁
    0.35
    лению
    0.35
    ських
    0.35
    ierenden
    0.35
    েন্টের
    0.35
    Activations Density 0.002%

    No Known Activations