© 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. 169851
    Prev
    Next
    INDEX
    Explanations

    BBC

    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
    英
    0.48
     영국
    0.46
     البريط
    0.42
     ещё
    0.42
     Englishman
    0.42
     Brit
    0.41
     britann
    0.41
     inglese
    0.41
     brit
    0.41
     英
    0.41
    POSITIVE LOGITS
    FOUR
    0.59
     FOUR
    0.57
    Four
    0.55
     Four
    0.54
    THREE
    0.50
     四
    0.49
     Three
    0.48
    四
    0.47
     POLIT
    0.46
     ನಾಲ್
    0.46
    Activations Density 0.000%

    No Known Activations