© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52945
    Prev
    Next
    INDEX
    Explanations

    redirect calls in flask

    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_30_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
    middot
    0.37
    ondissement
    0.36
    𐱃
    0.36
     ſt
    0.35
    ClassName
    0.35
    pyridine
    0.35
     कटे
    0.34
    安定
    0.34
     پیک
    0.34
     දි
    0.34
    POSITIVE LOGITS
     Controller
    0.39
     library
    0.38
     controller
    0.38
     तुला
    0.38
     eyew
    0.37
     then
    0.36
     от
    0.36
    扮
    0.36
     actually
    0.35
     আইনের
    0.35
    Activations Density 0.001%

    No Known Activations