© 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
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194185
    Prev
    Next
    INDEX
    Explanations

    language settings

    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_15_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
    发展
    0.52
    )}$,
    0.51
    开拓
    0.48
     các
    0.44
    പ്പെടെ
    0.42
    陆续
    0.42
    lde
    0.41
    Xia
    0.41
     कॉलोनी
    0.41
    GraphQl
    0.41
    POSITIVE LOGITS
     oka
    0.54
     touches
    0.53
    𝙛
    0.52
     fleurs
    0.52
     Portugal
    0.51
     Z
    0.50
     NBC
    0.50
    𝗳
    0.49
     oración
    0.49
    elé
    0.49
    Activations Density 0.000%

    No Known Activations