© 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. 8267
    Prev
    Next
    INDEX
    Explanations

    Minister for

    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
     както
    2.76
    \!\
    2.71
    𝐞
    2.57
     Tutto
    2.53
     всего
    2.49
    ︎
    2.41
     preuve
    2.39
    υτό
    2.39
     więcej
    2.35
     thirds
    2.29
    POSITIVE LOGITS
    ер
    2.69
    ים
    2.62
    nod
    2.52
    ют
    2.46
    日起
    2.43
    ድግዳ
    2.39
    s
    2.36
    Н
    2.32
    OrDefault
    2.26
     aikana
    2.25
    Activations Density 0.001%

    No Known Activations