© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18226
    Prev
    Next
    INDEX
    Explanations

    recognizing or realizing

    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_40_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
    penguin
    0.36
     Tsun
    0.35
     প্রতি
    0.35
     گرم
    0.35
    othyroidism
    0.34
     வ
    0.34
     শাও
    0.34
    蕩
    0.34
    ನ್ನು
    0.33
     séances
    0.33
    POSITIVE LOGITS
     recognizing
    1.81
     Recognizing
    1.79
    Recogn
    1.76
     realizing
    1.73
     realize
    1.72
     recognising
    1.70
    意识到
    1.70
     recognizes
    1.69
     realizes
    1.69
     realization
    1.68
    Activations Density 0.248%

    No Known Activations