© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34148
    Prev
    Next
    INDEX
    Explanations

    worm

    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
     sayılı
    0.41
    猶
    0.40
    ായ്
    0.39
     bundle
    0.39
     exposition
    0.39
     Torah
    0.38
    bund
    0.37
     Terror
    0.36
     Bundle
    0.36
    bundle
    0.36
    POSITIVE LOGITS
    renzia
    0.36
    穢
    0.34
     반지름
    0.34
    ;">
    0.34
     发表
    0.34
     עד
    0.33
    ^{+},
    0.33
    ytically
    0.33
    elliptic
    0.33
    ленно
    0.33
    Activations Density 0.007%

    No Known Activations