© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24145
    Prev
    Next
    INDEX
    Explanations

    company names

    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_56_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
     (/
    0.62
     Quotes
    0.48
     /ˈ
    0.46
    Quotes
    0.38
     އި
    0.37
     Quote
    0.36
     geboren
    0.36
    (/
    0.34
     quotes
    0.33
     hecho
    0.33
    POSITIVE LOGITS
     aka
    0.38
     specialise
    0.37
     AKA
    0.36
     specialises
    0.36
    трите
    0.36
    Founder
    0.35
    削
    0.35
     specialize
    0.34
    ixi
    0.33
    Formerly
    0.33
    Activations Density 0.017%

    No Known Activations