© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63312
    Prev
    Next
    INDEX
    Explanations

    academic and professional subjects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     remembering
    0.45
     form
    0.42
    
    0.40
     skipping
    0.40
     ruling
    0.39
     Skipping
    0.39
     shouting
    0.39
     letting
    0.38
     Pays
    0.38
     surveying
    0.38
    POSITIVE LOGITS
     &
    0.52
    Ensure
    0.44
     inciting
    0.41
    ens
    0.40
     Ensure
    0.39
     اختصاص
    0.39
     आकर्षण
    0.38
    確保
    0.37
    ]&
    0.37
     ensure
    0.37
    Activations Density 0.001%

    No Known Activations