© 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. 3097
    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
    ت
    2.69
    ία
    2.58
    ام
    2.52
    ۰۰
    2.45
     semangat
    2.36
    śle
    2.35
    然後
    2.32
    чным
    2.31
     stomachs
    2.31
    blown
    2.29
    POSITIVE LOGITS
    ک
    2.93
     leftmost
    2.83
     envisaged
    2.69
     arterioles
    2.64
    们的
    2.57
    stir
    2.56
    ご
    2.54
    longrightarrow
    2.53
    estion
    2.52
    rt
    2.51
    Activations Density 0.034%

    No Known Activations