© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173012
    Prev
    Next
    INDEX
    Explanations

    can provide

    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
     instructions
    0.36
    algèbre
    0.35
     Segmentation
    0.35
     fournis
    0.35
    Ğ
    0.34
     cannot
    0.34
    oss
    0.33
     manner
    0.33
     playlist
    0.33
     Operating
    0.32
    POSITIVE LOGITS
    ytoin
    0.36
    迢
    0.35
    vaient
    0.34
     phenytoin
    0.34
    CreateModel
    0.34
    ก่อ
    0.33
    ূতন
    0.33
     heo
    0.33
     गव
    0.32
    ណ៌
    0.32
    Activations Density 0.050%

    No Known Activations