© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118612
    Prev
    Next
    INDEX
    Explanations

    python flask react html javascript

    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_27_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
    ^+,
    0.39
     कॉनकॉर्ड
    0.36
    maintained
    0.36
    ày
    0.35
    green
    0.35
     añadió
    0.35
    Enfin
    0.35
     hatten
    0.35
    concentration
    0.34
    cN
    0.34
    POSITIVE LOGITS
     Employee
    0.36
     Flash
    0.34
     rep
    0.34
     검
    0.34
     algebraically
    0.33
     Grill
    0.33
     Drawing
    0.33
     Online
    0.31
     Learn
    0.31
     Krank
    0.31
    Activations Density 0.002%

    No Known Activations