© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41613
    Prev
    Next
    INDEX
    Explanations

    combine like terms

    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_22_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
     sebagai
    0.15
    ebug
    0.14
    as
    0.14
     &
    0.14
    -
    0.14
     vanes
    0.13
     ۽
    0.13
     nasel
    0.13
    _
    0.13
     atau
    0.13
    POSITIVE LOGITS
    ্যালেঞ্জ
    0.13
    接收
    0.13
     מיי
    0.13
     받고
    0.13
    usingCamera
    0.13
     পড়ার
    0.13
    igable
    0.13
     Bildern
    0.12
     approximately
    0.12
    perspective
    0.12
    Activations Density 0.003%

    No Known Activations