© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136924
    Prev
    Next
    INDEX
    Explanations

    First Law

    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_12_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
     ಕಂಚ
    0.20
    вчи
    0.19
     valuing
    0.19
    ﺗ
    0.18
     conversion
    0.18
     trapping
    0.18
     weapons
    0.18
    determination
    0.18
     classifying
    0.17
     devaluation
    0.17
    POSITIVE LOGITS
    साठी
    0.19
    Er
    0.18
     portug
    0.17
    t
    0.17
    D
    0.17
    Not
    0.17
    Pour
    0.17
    Ha
    0.17
    On
    0.17
    Only
    0.16
    Activations Density 0.005%

    No Known Activations