© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132546
    Prev
    Next
    INDEX
    Explanations

    programming language traits

    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_1_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
    }
    1.18
    １
    1.11
     nasce
    1.05
    '
    1.04
     сент
    0.98
    на
    0.97
     faça
    0.96
    不過
    0.93
    可以
    0.91
     он
    0.91
    POSITIVE LOGITS
    지
    1.24
    ם
    1.02
    in
    0.97
    ت
    0.96
     d
    0.94
    ist
    0.93
    مة
    0.91
    ב
    0.91
    the
    0.90
    pm
    0.90
    Activations Density 0.000%

    No Known Activations