© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1358
    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_12_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
    design
    0.18
    ī
    0.16
    ship
    0.16
     age
    0.16
    da
    0.16
    ്യം
    0.15
    iza
    0.15
     portability
    0.15
     периода
    0.15
    sellers
    0.15
    POSITIVE LOGITS
    滪
    0.20
     Subset
    0.18
     necesaria
    0.17
     Gentle
    0.16
     Анти
    0.16
     Nxf
    0.16
     uneasy
    0.15
     Relaxation
    0.15
    |.|.|
    0.15
    のため
    0.15
    Activations Density 1.771%

    No Known Activations