© 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. 8428
    Prev
    Next
    INDEX
    Explanations

    php code declarations

    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
    ه
    0.94
    ıyla
    0.84
    ا
    0.83
    ங்கிணை
    0.75
    an
    0.74
    ك
    0.73
     contend
    0.72
     हज़ार
    0.72
     oku
    0.71
     engag
    0.71
    POSITIVE LOGITS
    ل
    1.00
     Anche
    0.78
    愎
    0.74
    cao
    0.73
    ﺄ
    0.73
     docket
    0.72
    場合は
    0.70
    لوں
    0.70
    ากหลาย
    0.70
    pani
    0.70
    Activations Density 0.002%

    No Known Activations