© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    \end{document}

    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
    ה
    2.25
    ست
    2.25
    اد
    2.06
     liga
    2.03
    ר
    2.00
    М
    1.99
     sò
    1.97
     dacă
    1.97
    tà
    1.96
     dira
    1.93
    POSITIVE LOGITS
    o
    3.01
    肓
    2.40
    opacity
    2.38
    an
    2.29
    nie
    2.28
    menus
    2.24
    tenance
    2.24
     eager
    2.23
    ம்
    2.23
     kepentingan
    2.23
    Activations Density 0.000%

    No Known Activations