© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3829
    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
    د
    4.00
    س
    2.81
    quela
    2.64
     spraw
    2.59
     indel
    2.58
    ع
    2.54
    ার
    2.49
    𝘯
    2.45
    у
    2.38
    𝘧
    2.36
    POSITIVE LOGITS
    taa
    2.54
    tion
    2.49
    {}".
    2.16
    ió
    2.11
     θα
    2.07
     HomeComponent
    2.06
    radas
    2.03
    鈥
    2.01
    UMNS
    1.99
     Invited
    1.97
    Activations Density 0.017%

    No Known Activations