© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7015
    Prev
    Next
    INDEX
    Explanations

    input type="text"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    о
    2.32
    辦法
    2.24
    er
    2.19
    erà
    2.18
    і
    2.18
    ='
    2.14
    ్
    2.12
    지
    2.05
    ாக
    2.04
    然而
    2.01
    POSITIVE LOGITS
     inflicting
    2.82
    años
    2.76
    
    2.62
    কাণ্ড
    2.50
     traversing
    2.40
    𝗺
    2.40
    esc
    2.37
    健全
    2.37
    ول
    2.36
     illustrates
    2.33
    Activations Density 0.011%

    No Known Activations