© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46615
    Prev
    Next
    INDEX
    Explanations

    forts and curtains

    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_13_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
    নগর
    0.36
    cir
    0.36
    <unused82>
    0.35
     عشر
    0.35
    єте
    0.35
     okolo
    0.35
     nDims
    0.35
    シティ
    0.35
     wrench
    0.34
     വരു
    0.34
    POSITIVE LOGITS
     curtains
    0.49
     curtain
    0.46
     Curtain
    0.45
     panneau
    0.44
    Rosa
    0.42
     Dermat
    0.41
    W
    0.41
    C
    0.41
     Cora
    0.40
     PANEL
    0.39
    Activations Density 0.030%

    No Known Activations