© 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. 3541
    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
    ти
    2.53
     soundness
    2.37
    瓏
    2.33
    я
    2.32
    tu
    2.28
    Km
    2.27
    NaN
    2.27
    \%),
    2.27
    \%)
    2.26
    珑
    2.26
    POSITIVE LOGITS
    ки
    3.11
     vives
    2.80
    ʟ
    2.59
    on
    2.45
    ᴛ
    2.42
    州市
    2.38
    多い
    2.34
    ik
    2.29
     ټول
    2.24
    y
    2.22
    Activations Density 0.034%

    No Known Activations