© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1573
    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
    𝒇
    1.50
    encour
    1.46
     Typography
    1.45
    ниях
    1.43
    ﺏ
    1.42
     Flexibility
    1.41
    𝒆
    1.39
    änder
    1.38
    𝙩
    1.37
     जियोग्राफी
    1.37
    POSITIVE LOGITS
    ki
    1.90
    ot
    1.65
    у
    1.54
    er
    1.53
    ic
    1.50
    ки
    1.48
    ر
    1.46
    jenigen
    1.46
    ка
    1.44
    ir
    1.44
    Activations Density 0.006%

    No Known Activations