© 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. 14395
    Prev
    Next
    INDEX
    Explanations

    Maven, Gradle, plugins

    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
    |
    0.19
    l
    0.17
    ।
    0.17
    с
    0.17
    ey
    0.17
    its
    0.17
    কট
    0.17
    и
    0.17
     |
    0.16
    altra
    0.16
    POSITIVE LOGITS
    zou
    0.20
     subsystem
    0.20
     gazebo
    0.19
     TTS
    0.19
     JUnit
    0.19
     piezo
    0.19
     goomba
    0.19
     ferroc
    0.19
     pom
    0.18
     Harrier
    0.18
    Activations Density 0.004%

    No Known Activations