© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212404
    Prev
    Next
    INDEX
    Explanations

    misspellings like wolrd, monde, welt

    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_5_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
    0
    1.38
    ۰
    1.25
    h
    1.16
     t
    1.10
     Minist
    1.04
     in
    1.02
    <0x80>
    1.01
     internasional
    1.01
    IA
    1.00
     the
    0.99
    POSITIVE LOGITS
    ו
    1.56
    ل
    1.52
    л
    1.36
    مي
    1.34
    kého
    1.34
    on
    1.31
    ب
    1.30
    ता
    1.27
    ا
    1.24
    مان
    1.23
    Activations Density 0.004%

    No Known Activations