© 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. 122683
    Prev
    Next
    INDEX
    Explanations

    region of interest

    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
     a
    0.84
    :
    0.73
    ма
    0.70
    )
    0.70
     to
    0.63
     ammon
    0.63
     import
    0.63
     arrangements
    0.62
    arg
    0.61
    ]
    0.59
    POSITIVE LOGITS
    。
    0.85
    ри
    0.73
    ۔
    0.73
    ।
    0.71
    ።
    0.68
     મદદ
    0.66
    。(
    0.66
    。",
    0.63
    。【
    0.63
     โร
    0.63
    Activations Density 0.001%

    No Known Activations