© 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. 3117
    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
    й
    3.80
    न
    3.18
     tieto
    2.88
     coronae
    2.88
    ਰ
    2.87
    𝑑
    2.77
    PLAYS
    2.75
    ER
    2.73
    neath
    2.72
    śmy
    2.71
    POSITIVE LOGITS
    ات
    2.97
    त
    2.72
    evre
    2.59
    та
    2.51
    з
    2.43
    야
    2.38
    ں
    2.38
    s
    2.36
    alada
    2.34
    tableLayoutPanel
    2.30
    Activations Density 0.060%

    No Known Activations