© 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. 1512
    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
     기울
    1.14
     सुना
    1.13
     ormai
    1.07
     আরেক
    1.05
     явления
    1.04
    شاہ
    1.04
    insular
    1.03
    丁
    1.02
    त
    1.01
    شاه
    1.01
    POSITIVE LOGITS
    ра
    1.34
    orems
    1.30
    ting
    1.22
    the
    1.21
    έ
    1.20
    
    1.16
    ❏
    1.16
     savor
    1.15
    l
    1.15
    itudinal
    1.13
    Activations Density 0.237%

    No Known Activations