© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 284
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    are
    1.92
    winding
    1.89
     akin
    1.86
    ufficient
    1.83
    ใบ
    1.81
     indisc
    1.77
    𝖽
    1.74
     NIT
    1.71
    ingly
    1.69
     extant
    1.68
    POSITIVE LOGITS
    ли
    2.56
    ت
    2.07
    ۰۰
    2.06
     Anmeldung
    1.82
     pomoć
    1.82
     dessen
    1.78
    esgue
    1.78
    यह
    1.78
     cesse
    1.76
     działania
    1.75
    Activations Density 0.071%

    No Known Activations