© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239215
    Prev
    Next
    INDEX
    Explanations

    coordinates: latitude longitude

    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_25_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
     glLightfv
    0.38
    羧
    0.38
     atténuées
    0.38
    Ꭸ
    0.36
    pyrazin
    0.35
     финансовых
    0.35
    ClearedBy
    0.34
     декла
    0.34
     தேவையான
    0.33
    ICAN
    0.33
    POSITIVE LOGITS
     not
    0.46
      
    0.41
     a
    0.41
     and
    0.40
     Bag
    0.40
    -
    0.39
     variable
    0.37
     Not
    0.37
     sharply
    0.37
     divided
    0.36
    Activations Density 0.001%

    No Known Activations