© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1806
    Prev
    Next
    INDEX
    Explanations

    exam or grade level

    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_39_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
    肩
    0.36
    productivity
    0.35
    醍
    0.33
     naturally
    0.32
    Halloween
    0.32
    وزر
    0.31
     gospel
    0.31
    Spell
    0.31
    нер
    0.30
    ोड
    0.30
    POSITIVE LOGITS
    卋
    0.34
     THEORY
    0.34
     teórico
    0.33
     Emery
    0.33
     subjekt
    0.33
     mundo
    0.32
     II
    0.32
     Mc
    0.32
    htt
    0.32
     Theory
    0.32
    Activations Density 0.022%

    No Known Activations