© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46587
    Prev
    Next
    INDEX
    Explanations

    th

    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_10_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
    ق
    0.54
    ش
    0.52
    杫
    0.50
    us
    0.48
    رض
    0.44
    ން
    0.44
     invers
    0.43
     পোকামাক
    0.43
    plante
    0.43
    fins
    0.43
    POSITIVE LOGITS
     seventh
    0.49
    with
    0.46
    o
    0.43
     Seventh
    0.43
     e
    0.43
    e
    0.43
     GR
    0.43
     sixth
    0.42
    about
    0.42
     żeby
    0.42
    Activations Density 0.019%

    No Known Activations