© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197402
    Prev
    Next
    INDEX
    Explanations

    realize

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Per
    1.63
     PER
    1.55
     Per
    1.53
     пер
    1.48
    per
    1.47
     per
    1.43
    PER
    1.36
     퍼
    1.27
     Пер
    1.26
     Perr
    1.15
    POSITIVE LOGITS
     realization
    1.11
     realizing
    1.03
     realising
    1.01
     realiz
    0.99
     realized
    0.99
     realisation
    0.98
     realize
    0.97
     realise
    0.97
     realizations
    0.95
     realised
    0.92
    Activations Density 0.152%

    No Known Activations