© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197988
    Prev
    Next
    INDEX
    Explanations

    safety and organizations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     oliva
    0.42
     Oliva
    0.42
    mbr
    0.39
    зне
    0.38
    elizmente
    0.38
    址
    0.38
    BL
    0.37
    र्भ
    0.36
     CDR
    0.36
    unción
    0.36
    POSITIVE LOGITS
    ogam
    0.47
    Importer
    0.40
     imid
    0.39
    ımın
    0.38
    gaxModule
    0.38
    Cy
    0.37
    incar
    0.37
    歳
    0.37
    पया
    0.37
    htaking
    0.37
    Activations Density 0.016%

    No Known Activations