© 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-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    achieves, competitive, better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_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
    orges
    0.40
     環
    0.39
     商品
    0.39
    乐
    0.38
    殡
    0.38
     продукции
    0.37
    殯
    0.37
    esteps
    0.36
    ＊
    0.36
     choir
    0.35
    POSITIVE LOGITS
     Mono
    0.39
     Kellogg
    0.38
    Mono
    0.38
     Nexus
    0.38
     Penet
    0.38
    Nexus
    0.37
    penet
    0.37
    茲
    0.37
    IMUM
    0.36
    factual
    0.36
    Activations Density 0.061%

    No Known Activations