© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85052
    Prev
    Next
    INDEX
    Explanations

    share in comments or share your

    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_23_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
    лата
    0.42
     sinar
    0.42
    метр
    0.41
     markup
    0.38
     SOLUTION
    0.38
     ergeben
    0.38
    磪
    0.38
    陘
    0.38
     BSData
    0.38
     Sonja
    0.38
    POSITIVE LOGITS
     pharmaceutical
    0.42
    vi
    0.39
    /-
    0.38
     "
    0.38
     electronics
    0.38
    Conditional
    0.37
     Medicines
    0.37
     “
    0.37
     চলচ্
    0.36
    }}_{
    0.35
    Activations Density 0.002%

    No Known Activations