© 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. 3063
    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
     aftermath
    2.52
     Tatsache
    2.37
     separable
    2.33
     myeloid
    2.32
     misdemeanor
    2.22
     nimet
    2.20
    𝗱
    2.19
    ଼
    2.17
     upris
    2.16
     deceived
    2.13
    POSITIVE LOGITS
    к
    2.15
    اتی
    2.10
    ज
    2.02
    ą
    2.01
    に
    1.94
    um
    1.91
    可以将
    1.90
    k
    1.81
    婿
    1.73
    கள்
    1.70
    Activations Density 0.034%

    No Known Activations