© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47925
    Prev
    Next
    INDEX
    Explanations

    knowledge

    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_10_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
    ،
    0.46
     модель
    0.41
     significative
    0.36
     exceptionnelle
    0.36
    نید
    0.36
     압
    0.35
     роль
    0.34
    }^{*}$,
    0.33
     linéaire
    0.33
     traditionnelle
    0.33
    POSITIVE LOGITS
     knowledge
    0.70
     Knowledge
    0.62
    knowledge
    0.61
    Knowledge
    0.60
    知識
    0.55
    _
    0.51
    知识
    0.48
     the
    0.47
     pengetahuan
    0.46
    H
    0.46
    Activations Density 0.033%

    No Known Activations