© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1945
    Prev
    Next
    INDEX
    Explanations

    percent sign

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    Cub
    0.38
    Some
    0.38
     suppliers
    0.38
    ឡើង
    0.37
     vitally
    0.37
     Algunas
    0.36
     magas
    0.36
    ╹
    0.35
    িয়াছিল
    0.35
    bcb
    0.35
    POSITIVE LOGITS
    hitva
    0.42
    კო
    0.40
     koa
    0.38
     je
    0.38
    साय
    0.37
    ની
    0.36
    基
    0.36
    绥
    0.36
    ymology
    0.36
    isson
    0.35
    Activations Density 0.017%

    No Known Activations