© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1591
    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
    \,.
    0.48
    atical
    0.46
    \!\
    0.45
    시고
    0.45
     shameless
    0.44
    ❷
    0.44
     将
    0.44
    o
    0.44
    jenigen
    0.43
    将
    0.43
    POSITIVE LOGITS
    ER
    0.52
     poter
    0.52
     nick
    0.46
     dépour
    0.44
     pohon
    0.44
    ンプル
    0.44
    plicate
    0.43
    geht
    0.42
    ල්
    0.42
    вени
    0.42
    Activations Density 0.400%

    No Known Activations