© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215211
    Prev
    Next
    INDEX
    Explanations

    "NewJeans", "new job", "condition", "frequency"

    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_16_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
     baryons
    0.57
     regressions
    0.57
    
    0.55
    ᵚ
    0.52
     অপর্ণ
    0.52
    谌
    0.52
     síntomas
    0.49
    PlatformTarget
    0.48
    ஜ
    0.48
     Ressourcen
    0.48
    POSITIVE LOGITS
     Comple
    0.46
     يح
    0.44
     ci
    0.44
     quis
    0.43
     Chips
    0.42
     '!
    0.42
     enforces
    0.41
     will
    0.41
     '
    0.40
     brings
    0.40
    Activations Density 0.000%

    No Known Activations