© 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. 8348
    Prev
    Next
    INDEX
    Explanations

    Content-Type header

    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
     ounce
    2.87
     Personally
    2.77
    я
    2.71
    ма
    2.71
    烃
    2.62
     contralateral
    2.61
    nect
    2.60
    ︎
    2.52
     admirable
    2.51
    ضه
    2.49
    POSITIVE LOGITS
     eben
    2.81
    𝗱
    2.55
    ্ট
    2.51
    ها
    2.45
    ра
    2.35
    ことから
    2.29
     springboard
    2.20
    ută
    2.18
     pues
    2.16
    Р
    2.16
    Activations Density 0.045%

    No Known Activations