© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44523
    Prev
    Next
    INDEX
    Explanations

    anymore remnant

    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_22_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
     Deadly
    0.38
    ನು
    0.32
    ^+
    0.31
     Toxicol
    0.31
     جانا
    0.31
    騇
    0.30
     Ná
    0.30
     {:.
    0.30
    CONCLUSION
    0.30
    眈
    0.30
    POSITIVE LOGITS
     anymore
    0.40
     remnants
    0.40
     remnant
    0.38
     structure
    0.36
    不再
    0.34
     left
    0.33
     intact
    0.33
     retains
    0.33
    ז
    0.33
     band
    0.32
    Activations Density 0.042%

    No Known Activations