© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42778
    Prev
    Next
    INDEX
    Explanations

    any existing or specific

    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
    拿下
    0.38
    くまで
    0.37
     ജില്ലാ
    0.35
     defray
    0.35
    녘
    0.35
     Vor
    0.35
    convolve
    0.35
    芎
    0.34
    असल
    0.34
    മാക
    0.33
    POSITIVE LOGITS
    тали
    0.35
    ugian
    0.34
     következő
    0.33
     mandated
    0.30
    陘
    0.30
    िरी
    0.30
    Greeting
    0.30
    Mask
    0.29
    rds
    0.29
    ल्दी
    0.29
    Activations Density 0.007%

    No Known Activations