© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116497
    Prev
    Next
    INDEX
    Explanations

    class followed by noun

    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_27_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
    BUSINESS
    0.42
     ವರ್
    0.42
    ERSHIP
    0.40
    дут
    0.40
     በፍ
    0.40
    LOVE
    0.39
    Р
    0.39
    шат
    0.38
     mainWindow
    0.38
    정
    0.38
    POSITIVE LOGITS
     landet
    0.39
     fabricant
    0.37
    gios
    0.37
     coûte
    0.36
    It
    0.35
     limite
    0.35
    ņem
    0.35
    newline
    0.35
    <0xAA>
    0.35
    经费
    0.35
    Activations Density 0.000%

    No Known Activations