© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171688
    Prev
    Next
    INDEX
    Explanations

    as ... as

    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_20_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
    铊
    0.40
     Passes
    0.38
    \|^{
    0.38
    δος
    0.37
     hår
    0.37
    लिटी
    0.37
     Jamaica
    0.37
     وآ
    0.37
    ъл
    0.36
    ષ્ણા
    0.36
    POSITIVE LOGITS
    paragraph
    0.44
    anyag
    0.42
    pInBuffer
    0.42
     binoculars
    0.41
    automation
    0.41
    イメージ
    0.41
     constitutes
    0.41
     ਬ
    0.40
    NgModule
    0.40
    kfollowers
    0.40
    Activations Density 0.001%

    No Known Activations