© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196387
    Prev
    Next
    INDEX
    Explanations

    kilometers or units

    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_4_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
     neighborhoods
    0.96
     be
    0.95
     rutrum
    0.93
     not
    0.88
     vand
    0.85
    ->
    0.85
        
    0.84
     state
    0.84
     foreclosure
    0.83
     woning
    0.83
    POSITIVE LOGITS
    는
    1.17
    ה
    1.02
    נ
    0.95
    monotonic
    0.94
    чи
    0.93
    five
    0.88
    ш
    0.88
    four
    0.87
    я
    0.86
    ۔
    0.86
    Activations Density 0.001%

    No Known Activations