© 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. 45653
    Prev
    Next
    INDEX
    Explanations

    mostly followed by descriptive clause

    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
     formContext
    0.32
     fusible
    0.29
    YNAMIC
    0.27
     diffusive
    0.27
    Purg
    0.27
    ഈ
    0.27
     Zeitschr
    0.27
    氖
    0.27
    寯
    0.27
     espaços
    0.26
    POSITIVE LOGITS
    alas
    0.30
    asses
    0.29
    ras
    0.28
    wall
    0.28
    imat
    0.28
    imming
    0.27
    ograf
    0.27
    imb
    0.26
    iga
    0.26
     not
    0.26
    Activations Density 0.004%

    No Known Activations