© 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. 7446
    Prev
    Next
    INDEX
    Explanations

    @ symbol followed by other, names, unique, utf, pdf

    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
    ु
    1.10
    বীন্দ্রনাথ
    1.07
    менение
    1.06
    ן
    1.03
    port
    0.97
     synonymous
    0.95
     Memorandum
    0.94
    odore
    0.94
    𝓃
    0.93
    ]'
    0.93
    POSITIVE LOGITS
    ため
    1.27
    sheets
    1.01
    f
    1.01
    𝗴
    0.97
    ف
    0.95
    ग्रस्त
    0.93
    gst
    0.90
    hende
    0.89
     ganger
    0.89
    forschung
    0.88
    Activations Density 0.001%

    No Known Activations