© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121707
    Prev
    Next
    INDEX
    Explanations

    using declaration

    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_37_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
    cient
    0.42
    ዙ
    0.40
    feels
    0.38
     grille
    0.36
    
    0.36
     outflows
    0.36
     console
    0.36
    setView
    0.35
    സ്തു
    0.35
    medal
    0.35
    POSITIVE LOGITS
    kez
    0.43
    迪
    0.41
    obium
    0.41
     VERT
    0.40
    攷
    0.40
     DIGITAL
    0.40
    oceras
    0.40
    叅
    0.40
    وپ
    0.39
    ڈنگ
    0.39
    Activations Density 0.000%

    No Known Activations