© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35288
    Prev
    Next
    INDEX
    Explanations

    data validation

    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_11_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
    ग्रीकल्चर
    0.55
    Unsere
    0.52
    ၂
    0.51
    Request
    0.50
    Application
    0.50
    registro
    0.50
    JAVADOC
    0.50
    fahr
    0.50
    হিন্দু
    0.50
    ")]),
    0.50
    POSITIVE LOGITS
    ние
    0.50
    olith
    0.49
    ાદ
    0.49
     screenings
    0.45
     needs
    0.44
     talked
    0.43
     Св
    0.43
     manten
    0.42
     surprisingly
    0.42
     Ха
    0.42
    Activations Density 0.002%

    No Known Activations