© 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. 163551
    Prev
    Next
    INDEX
    Explanations

    `LL` followed by label dimension commands

    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
     conceivable
    0.44
    দেন
    0.42
    æn
    0.41
     ਉਨ੍ਹਾਂ
    0.41
     denke
    0.39
     élast
    0.39
     elastomer
    0.39
    𝕌
    0.39
    かもしれない
    0.38
     احتم
    0.38
    POSITIVE LOGITS
    il
    0.46
    land
    0.38
    alon
    0.38
    stack
    0.36
    熊
    0.36
    لية
    0.36
    lily
    0.36
    fig
    0.35
    Arthur
    0.35
     Lohia
    0.35
    Activations Density 0.010%

    No Known Activations