© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33749
    Prev
    Next
    INDEX
    Explanations

    scene graph Generation

    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_3_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
    Adams
    0.58
     Olaf
    0.57
    㫴
    0.57
    uant
    0.55
    Oh
    0.54
     Sigmund
    0.54
     DLP
    0.54
     Workmen
    0.53
    InstanceOf
    0.53
    嫄
    0.53
    POSITIVE LOGITS
     scenes
    0.94
     scene
    0.93
     escena
    0.92
    ။
    0.88
    ية
    0.84
    c
    0.84
    ید
    0.79
    Scene
    0.79
     Scene
    0.78
     scène
    0.77
    Activations Density 0.003%

    No Known Activations