© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30821
    Prev
    Next
    INDEX
    Explanations

    non-latin script start

    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_31_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
    )':
    0.42
     cerebral
    0.38
     햇
    0.38
    क्षिप्त
    0.37
     hour
    0.36
     Karten
    0.36
     cropped
    0.36
     képes
    0.36
    햇
    0.36
     poultry
    0.35
    POSITIVE LOGITS
    leda
    0.39
    Next
    0.38
     लगती
    0.38
    រ
    0.36
    帖
    0.35
    ldg
    0.35
    FBSDKGraph
    0.35
    legraph
    0.34
     सावंत
    0.34
     लगने
    0.34
    Activations Density 0.000%

    No Known Activations