© 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. 4920
    Prev
    Next
    INDEX
    Explanations

    all-star or all-inclusive

    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
    на
    1.94
    儡
    1.84
    acoli
    1.82
    ই
    1.73
     soldi
    1.73
    โอกาส
    1.71
    א
    1.69
     frameN
    1.68
    䡒
    1.61
    なります
    1.61
    POSITIVE LOGITS
    potion
    2.05
    ert
    1.85
    ingly
    1.82
    不
    1.79
    arı
    1.74
     majorité
    1.71
    ie
    1.71
    ন
    1.68
    ів
    1.62
     sở
    1.61
    Activations Density 0.036%

    No Known Activations