© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64937
    Prev
    Next
    INDEX
    Explanations

    P-complete, NP-complete

    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_41_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
     z
    0.94
     Z
    0.74
     ز
    0.73
    Z
    0.66
    z
    0.63
    ｚ
    0.63
     з
    0.61
     ज़
    0.55
     ז
    0.55
    𝑧
    0.55
    POSITIVE LOGITS
     matches
    0.43
    uose
    0.38
     upsets
    0.38
    ILLIPS
    0.38
     Smash
    0.37
     छी
    0.37
     match
    0.37
     matchs
    0.36
     shake
    0.35
     офі
    0.35
    Activations Density 0.000%

    No Known Activations