© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6508
    Prev
    Next
    INDEX
    Explanations

    server

    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
    к
    2.66
    ◁
    2.54
    cssMode
    2.53
    اٹ
    2.51
    ालय
    2.43
     welds
    2.41
    𝓗
    2.39
    pexels
    2.38
    ക്കുറിച്ച്
    2.36
     filesystem
    2.35
    POSITIVE LOGITS
    i
    2.71
    iz
    2.17
    ি
    2.04
    ständig
    2.01
    י
    1.94
    𝑖
    1.93
    imate
    1.93
     pró
    1.92
    licht
    1.91
    ing
    1.86
    Activations Density 0.001%

    No Known Activations