© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199658
    Prev
    Next
    INDEX
    Explanations

    git commit SHA

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     खिच
    0.40
    浜
    0.39
     Vaill
    0.38
    ಬ್
    0.36
     Timm
    0.35
     havoc
    0.35
    बुक
    0.34
     दिलाया
    0.34
     sur
    0.34
     happened
    0.34
    POSITIVE LOGITS
     Spacer
    0.38
     Reference
    0.38
     sbParams
    0.38
    ạ
    0.37
     참고
    0.37
    reference
    0.37
    inental
    0.37
    ອອກ
    0.37
     EMERG
    0.36
    स्को
    0.36
    Activations Density 0.002%

    No Known Activations