© 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. 1649
    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
    0.30
     കാല
    0.30
     בר
    0.30
    iegler
    0.29
    G
    0.28
    ksom
    0.28
    례
    0.28
    Ago
    0.28
    avn
    0.28
    บาล
    0.28
    POSITIVE LOGITS
     coveted
    0.49
     pampered
    0.48
    awaited
    0.48
     cuddle
    0.44
     dubbed
    0.44
    proclaimed
    0.43
    빱
    0.42
    riumph
    0.42
    llama
    0.42
     junkie
    0.42
    Activations Density 0.095%

    No Known Activations