© 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. 7390
    Prev
    Next
    INDEX
    Explanations

    DOI links and academic publishers

    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
    ح
    2.42
    തിരെ
    2.39
    Դ
    2.29
    uatan
    2.16
     pejabat
    2.11
    gments
    2.10
    ᠯ
    2.09
    酐
    2.08
     logró
    2.08
    দ
    2.07
    POSITIVE LOGITS
     plt
    2.80
    জনের
    2.73
    ू
    2.67
     lour
    2.40
    
    2.22
     indetermin
    2.20
    ר
    2.16
    ISBN
    2.16
    ン
    2.14
    plt
    2.14
    Activations Density 0.000%

    No Known Activations