© 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. 18819
    Prev
    Next
    INDEX
    Explanations

    GPU drivers

    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
    §
    0.49
    cylinder
    0.48
    oggetto
    0.48
    ச்சின்ன
    0.47
    ့်
    0.46
    orge
    0.46
    coords
    0.46
    placeholder
    0.45
    Benzoimidazole
    0.45
    이블
    0.44
    POSITIVE LOGITS
    (
    0.53
    憎
    0.47
     आरा
    0.46
    लाक
    0.45
     등의
    0.45
    People
    0.44
    나가
    0.44
    ➫
    0.44
     конферен
    0.44
     ગયો
    0.44
    Activations Density 0.004%

    No Known Activations