© 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. 1065
    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
    ᴄ
    2.54
     alimentar
    2.53
    n
    2.53
     απο
    2.45
    nk
    2.40
    ml
    2.32
     electrónicos
    2.32
    ="./
    2.29
    mib
    2.27
    rd
    2.23
    POSITIVE LOGITS
    ׁ
    2.78
     excitations
    2.67
    де
    2.60
    ЛЬ
    2.60
    ע
    2.51
    ITECTURE
    2.50
     /^
    2.49
    ఫ
    2.49
    tudo
    2.48
    الع
    2.46
    Activations Density 0.444%

    No Known Activations