© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129366
    Prev
    Next
    INDEX
    Explanations

    server virtualization

    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_1_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
     a
    1.68
     zum
    1.28
     công
    1.23
     article
    1.20
    ↵
    1.19
     étapes
    1.19
     atractivo
    1.17
     acceso
    1.16
     externe
    1.16
     macam
    1.16
    POSITIVE LOGITS
    I
    1.27
    But
    1.19
    that
    1.16
    Let
    1.13
    ні
    1.07
    If
    1.05
    By
    1.05
    That
    1.02
    For
    1.02
    Being
    1.02
    Activations Density 0.003%

    No Known Activations