© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212714
    Prev
    Next
    INDEX
    Explanations

    names and numbers

    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_43_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
    <unused96>
    0.40
     Foam
    0.39
     Police
    0.39
     Vehicle
    0.38
     traffickers
    0.38
    ഫോ
    0.37
     പോലീസ്
    0.37
    earch
    0.36
     অভিয
    0.36
     방향
    0.36
    POSITIVE LOGITS
    Hector
    0.50
     phyll
    0.46
     Hector
    0.43
    律
    0.39
    율
    0.39
     Héctor
    0.38
    cre
    0.38
    ولی
    0.36
    ছি
    0.36
    ছেন
    0.36
    Activations Density 0.001%

    No Known Activations