© 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. 41351
    Prev
    Next
    INDEX
    Explanations

    MMU memory management

    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
    ма
    0.89
    1
    0.81
    ਮ
    0.80
    ¹.
    0.78
    мі
    0.77
    the
    0.72
     устрой
    0.70
    あ
    0.70
    सा
    0.69
    ના
    0.69
    POSITIVE LOGITS
    -
    0.77
    i
    0.75
    b
    0.73
    )
    0.73
    ↵↵
    0.73
                    
    0.72
    <0x80>
    0.70
    ’
    0.70
                  
    0.70
    ي
    0.69
    Activations Density 0.003%

    No Known Activations