© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207763
    Prev
    Next
    INDEX
    Explanations

    code patterns and technical terms

    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_20_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
     staffers
    0.46
     FJ
    0.43
     outraged
    0.43
     impressed
    0.43
     l
    0.42
     Summer
    0.42
     Stones
    0.42
    ंभ
    0.41
     aliens
    0.41
     '?
    0.41
    POSITIVE LOGITS
    隼
    0.48
    tekn
    0.44
    ゐ
    0.44
    츠
    0.43
    团
    0.43
    REACTOR
    0.42
    unghi
    0.42
    리기
    0.42
    山市
    0.41
    technik
    0.41
    Activations Density 0.000%

    No Known Activations