© 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. 23882
    Prev
    Next
    INDEX
    Explanations

    educated

    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
     guess
    2.44
    Guess
    2.33
     Guess
    2.33
    guess
    2.31
     guessing
    1.76
     guesses
    1.73
    guessing
    1.62
    猜
    1.59
    guesses
    1.52
     guesswork
    1.44
    POSITIVE LOGITS
     educated
    1.50
     Educ
    1.32
    educated
    1.20
    Educ
    1.16
     educ
    1.07
     g
    1.02
     educating
    1.02
     शिक्षित
    1.00
     educate
    0.99
     Gu
    0.95
    Activations Density 0.167%

    No Known Activations