© 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. 5971
    Prev
    Next
    INDEX
    Explanations

    coloring, attention, learning

    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
    od
    2.00
     hasattr
    2.00
    šu
    1.98
    uzione
    1.87
    orrh
    1.86
    esimo
    1.79
    <unused688>
    1.79
    狞
    1.78
    čni
    1.75
    electrons
    1.73
    POSITIVE LOGITS
    SwapChain
    2.19
    Ûn
    2.10
    다른
    1.95
    豊かな
    1.93
    "",
    1.92
    ►
    1.87
    ㅢ
    1.84
    blind
    1.83
     proceeded
    1.82
    깔
    1.82
    Activations Density 0.036%

    No Known Activations