© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42417
    Prev
    Next
    INDEX
    Explanations

    Whiskey cocktail ingredient

    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_3_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
    ä
    0.75
    u
    0.74
    ので
    0.71
    عمل
    0.70
    dır
    0.70
    تين
    0.67
    ö
    0.67
    고
    0.66
     electrón
    0.66
    تور
    0.66
    POSITIVE LOGITS
    с
    0.58
     поверну
    0.57
    ﻈ
    0.57
     primordial
    0.57
    ի
    0.57
    presso
    0.56
     flexion
    0.55
    changed
    0.54
     depository
    0.54
     testament
    0.54
    Activations Density 0.000%

    No Known Activations