© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196026
    Prev
    Next
    INDEX
    Explanations

    words ending in 'on' or 'en'

    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_4_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
    م
    1.42
    as
    1.35
    在
    1.14
    в
    1.07
    ти
    1.04
    in
    1.02
    يد
    1.00
    os
    0.98
    ق
    0.91
    ం
    0.90
    POSITIVE LOGITS
    t
    1.05
    telling
    0.91
    tch
    0.84
    dL
    0.82
    tin
    0.82
    tte
    0.82
    tree
    0.79
    rg
    0.79
    trip
    0.78
    tumor
    0.77
    Activations Density 0.000%

    No Known Activations