© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78411
    Prev
    Next
    INDEX
    Explanations

    mean, *, AL, DT

    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_31_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
     يحت
    0.35
     czynności
    0.34
    嘧
    0.34
    Autocomplete
    0.34
    म्प्ट
    0.33
    ̬
    0.33
    ↺
    0.32
    Mau
    0.32
    🏚
    0.32
     hypothalam
    0.32
    POSITIVE LOGITS
     Co
    0.33
     uniformly
    0.33
     chamado
    0.33
    ாம
    0.32
    uniformly
    0.32
    ملك
    0.31
     named
    0.31
     EL
    0.31
     Escola
    0.31
     Mith
    0.31
    Activations Density 0.003%

    No Known Activations