© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31546
    Prev
    Next
    INDEX
    Explanations

    font-family and margin

    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_31_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
     buried
    0.42
     burying
    0.40
     bury
    0.38
     Bernadette
    0.38
     ceremonial
    0.37
     ścian
    0.36
    埋
    0.36
     Mud
    0.36
     Seç
    0.36
     Bernstein
    0.35
    POSITIVE LOGITS
    ข้อมูล
    0.37
     predictors
    0.37
     информацией
    0.37
    목
    0.37
    ngthen
    0.36
     informacje
    0.36
     backers
    0.36
    鄰
    0.35
    replic
    0.34
    ocrats
    0.34
    Activations Density 0.067%

    No Known Activations