© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37876
    Prev
    Next
    INDEX
    Explanations

    in short, conclusion, summary, essence

    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_11_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
     polysaccharide
    0.58
     odors
    0.58
    för
    0.55
     OFW
    0.55
     KGB
    0.54
    ک
    0.54
    दिग्ध
    0.52
     islets
    0.52
     antik
    0.52
     Osama
    0.52
    POSITIVE LOGITS
    -
    0.52
    n
    0.49
     felicidade
    0.47
     prace
    0.47
     zako
    0.46
     pluie
    0.46
     compless
    0.45
     recommand
    0.45
     corne
    0.45
    <0x9F>
    0.45
    Activations Density 0.027%

    No Known Activations