© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    PyPDF2 and code examples

    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
    
    2.62
    
    2.53
    ب
    2.48
    
    2.37
    сці
    2.20
    ি
    2.18
    স
    2.17
    ی
    2.16
    ইংরেজি
    2.16
    ت
    2.14
    POSITIVE LOGITS
    SHALL
    2.15
    sembling
    2.07
    sembled
    1.98
    igation
    1.97
     vicenda
    1.93
    SIBLE
    1.89
    権
    1.86
     perturbed
    1.86
     biri
    1.84
    versal
    1.83
    Activations Density 0.000%

    No Known Activations