© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118802
    Prev
    Next
    INDEX
    Explanations

    code block keywords

    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_27_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
     Societies
    0.41
    ;?>
    0.41
     Liabilities
    0.40
    させる
    0.39
     აქ
    0.39
    newL
    0.38
     बेस्ड
    0.38
     考え
    0.38
    鍑
    0.37
     エ
    0.37
    POSITIVE LOGITS
    ßer
    0.36
     ولكن
    0.35
     universe
    0.35
     nici
    0.35
     terci
    0.34
     universo
    0.33
     ninguna
    0.33
    iatica
    0.33
     (.
    0.33
     pero
    0.32
    Activations Density 0.000%

    No Known Activations