© 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. 8625
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
    нде
    2.36
    خ
    2.35
    тни
    2.17
    fprintf
    2.08
    ्युनिकेशन
    1.99
    alanine
    1.98
     Laufe
    1.95
     surround
    1.95
    ية
    1.94
     mnoho
    1.93
    POSITIVE LOGITS
    ר
    3.05
    enbach
    2.33
    পর্ব
    2.24
    drawing
    2.20
    ㇂
    2.19
    滘
    2.18
    ☇
    2.15
    iş
    2.15
     noqa
    2.13
    drawn
    2.12
    Activations Density 0.048%

    No Known Activations