© 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. 1257
    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
    ECTION
    1.58
    ه
    1.50
    सभी
    1.42
     mouve
    1.41
    ल
    1.40
    ники
    1.40
    𝙾
    1.39
    ர
    1.38
     thighs
    1.38
    न
    1.35
    POSITIVE LOGITS
    en
    1.94
    et
    1.88
    y
    1.73
    amble
    1.70
    el
    1.56
    <bos>
    1.54
    ek
    1.51
    ди
    1.35
    yed
    1.34
    etano
    1.32
    Activations Density 0.006%

    No Known Activations