© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 166779
    Prev
    Next
    INDEX
    Explanations

    Got

    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
    izadores
    0.25
    倦
    0.25
     cfg
    0.25
    ឡើង
    0.25
     уго
    0.24
     температуры
    0.24
     nuevamente
    0.24
     কমিটির
    0.24
    ogliamo
    0.24
     randomly
    0.24
    POSITIVE LOGITS
     Mounting
    0.26
     revolutionized
    0.25
    లువ
    0.24
     टेक्न
    0.24
    ложений
    0.24
    궁
    0.24
     環
    0.24
    ẳ
    0.24
     bik
    0.23
    واكب
    0.23
    Activations Density 0.004%

    No Known Activations