© 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. 3449
    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
    ܢ
    2.40
    ܢܐ
    2.40
     helplessly
    2.33
    ل
    2.32
    খানেই
    2.32
    ر
    2.28
     aggregating
    2.24
    lier
    2.23
    পন্ন
    2.22
    那天
    2.22
    POSITIVE LOGITS
     propi
    2.20
    ar
    2.17
    arom
    2.14
    zahl
    2.05
    ac
    2.03
    iv
    2.00
     корреспонд
    1.96
    激安
    1.95
    fell
    1.95
    ৈ
    1.93
    Activations Density 0.016%

    No Known Activations