© 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. 8659
    Prev
    Next
    INDEX
    Explanations

    JSON structure elements

    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
    o
    3.20
    ه
    2.94
    ../../../
    2.69
    friend
    2.67
    де
    2.66
    grade
    2.50
     ​​
    2.48
     chắc
    2.41
    项
    2.40
    اداسی
    2.37
    POSITIVE LOGITS
    ių
    3.46
    on
    3.44
    𝑑
    3.14
    ट
    3.12
    iction
    3.08
    ్
    3.01
     wits
    2.99
    ি
    2.95
    কর
    2.95
    cology
    2.91
    Activations Density 0.227%

    No Known Activations