© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36571
    Prev
    Next
    INDEX
    Explanations

    wideband networks

    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
    ﻪ
    0.66
    ו
    0.63
     despicable
    0.62
     والی
    0.61
     prawa
    0.61
    e
    0.60
    الی
    0.59
    が多く
    0.59
    ینی
    0.58
    も
    0.58
    POSITIVE LOGITS
     to
    1.02
    ل
    0.82
    to
    0.80
    的
    0.68
    fe
    0.67
    DC
    0.64
    ulk
    0.62
    나
    0.61
     то
    0.61
    )。
    0.61
    Activations Density 0.004%

    No Known Activations