© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65779
    Prev
    Next
    INDEX
    Explanations

    Co

    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_51_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
    වත
    0.37
    ,+\
    0.36
     Kral
    0.36
    젬
    0.36
    掝
    0.35
    沚
    0.35
    
    0.34
    ifadə
    0.34
    لین
    0.34
    otom
    0.33
    POSITIVE LOGITS
    Co
    2.70
     Co
    2.67
    co
    2.30
     co
    2.09
    CO
    2.05
     CO
    2.02
    <0xAA>
    1.91
    Coe
    1.85
     코
    1.84
     Coil
    1.79
    Activations Density 0.002%

    No Known Activations