© 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. 7279
    Prev
    Next
    INDEX
    Explanations

    arguments and debate

    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
    ل
    0.63
    ن
    0.59
    อ่อน
    0.55
    n
    0.54
    ng
    0.51
    getPage
    0.51
    சு
    0.50
    其他
    0.50
    k
    0.50
    การ
    0.50
    POSITIVE LOGITS
    sudo
    0.59
    даги
    0.58
    keiten
    0.57
     المحلي
    0.57
     Certains
    0.57
     cultivars
    0.55
    挲
    0.55
    ой
    0.54
     NOS
    0.54
    ита
    0.53
    Activations Density 0.400%

    No Known Activations