© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16847
    Prev
    Next
    INDEX
    Explanations

    linux distributions stability

    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_40_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
    Cross
    0.63
     Cross
    0.55
     cross
    0.52
    cross
    0.48
    CROSS
    0.47
     CROSS
    0.46
    跨
    0.43
     crossed
    0.41
    Syn
    0.38
    Mut
    0.38
    POSITIVE LOGITS
     stability
    0.36
    헐
    0.36
     stabilit
    0.36
     stickers
    0.36
     message
    0.35
    abhas
    0.35
    ंगामा
    0.34
     сообщение
    0.34
    浄
    0.34
     unions
    0.33
    Activations Density 0.034%

    No Known Activations