© 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. 7957
    Prev
    Next
    INDEX
    Explanations

    end-to-endpeer-to-peer

    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
    𝕞
    2.05
    व
    1.99
    Shortly
    1.91
    ูณ
    1.84
    ंत्रिक
    1.84
    𝕦
    1.69
    #!
    1.68
    #'
    1.68
    𝕖
    1.67
    ਆਂ
    1.65
    POSITIVE LOGITS
    ะ
    1.72
     Оста
    1.66
     Есть
    1.62
    蓣
    1.57
    ್‌
    1.55
    ળી
    1.55
    魎
    1.53
     Página
    1.51
     Saviour
    1.50
     reqParams
    1.48
    Activations Density 0.069%

    No Known Activations