© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142077
    Prev
    Next
    INDEX
    Explanations

    well, now

    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_12_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
     εκ
    0.59
     земе
    0.58
     з
    0.57
     คํา
    0.56
     energi
    0.56
     оре
    0.55
     importantly
    0.55
     graphon
    0.55
     в
    0.55
     ว
    0.55
    POSITIVE LOGITS
    rib
    0.64
    ق
    0.62
    泗
    0.62
    Τ
    0.57
    rc
    0.56
    لو
    0.56
    رب
    0.55
    رو
    0.55
    اش
    0.55
    ن
    0.55
    Activations Density 0.007%

    No Known Activations