© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14609
    Prev
    Next
    INDEX
    Explanations

    Montessori education

    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_13_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
     добро
    0.49
    рата
    0.49
     صہی
    0.48
     hài
    0.48
    preserving
    0.46
    instance
    0.46
     instances
    0.46
    ġ
    0.46
     monumento
    0.45
     fundraiser
    0.45
    POSITIVE LOGITS
     Stockholm
    0.59
    टका
    0.48
     Sweden
    0.48
     sagen
    0.48
    ću
    0.48
    ća
    0.47
    ći
    0.47
    ćem
    0.47
     ;$
    0.46
     Sverige
    0.46
    Activations Density 0.001%

    No Known Activations