© 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. 2506
    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
    나
    2.46
    히
    2.28
    А
    2.23
     এছাড়াও
    2.21
    そして
    2.20
    teenth
    2.20
    ं
    2.19
     variety
    2.16
    ц
    2.16
    ний
    2.15
    POSITIVE LOGITS
    ig
    3.10
    ер
    2.58
    يون
    2.30
    e
    2.27
    yen
    2.23
     propos
    2.20
    י
    2.18
    ebe
    2.15
    yx
    2.14
    ece
    2.13
    Activations Density 0.087%

    No Known Activations