© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80954
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast

    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_29_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
    imhe
    0.33
    പെ
    0.30
    一百
    0.29
    <\/
    0.29
    cheap
    0.27
    institutional
    0.27
     profesionales
    0.27
    二百
    0.27
    莢
    0.26
     PMID
    0.26
    POSITIVE LOGITS
    Municipio
    0.35
     moi
    0.31
    тки
    0.30
    噫
    0.30
     Zeta
    0.30
     miraculously
    0.30
     OTA
    0.28
     Nazar
    0.28
    तः
    0.28
     zeta
    0.28
    Activations Density 0.009%

    No Known Activations