© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15069
    Prev
    Next
    INDEX
    Explanations

    trend lines

    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_15_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
     уде
    0.29
    6
    0.28
     noticias
    0.28
     环境
    0.27
    3
    0.27
    F
    0.27
    ppo
    0.27
    There
    0.27
    '))
    0.27
     mã
    0.27
    POSITIVE LOGITS
    ൊക്കെ
    0.32
    ivesse
    0.31
    是从
    0.31
    RestorePolicy
    0.31
    getRoot
    0.30
    mány
    0.30
    deployRoot
    0.30
    仞
    0.29
     다시
    0.29
     જ્યાં
    0.28
    Activations Density 0.005%

    No Known Activations