© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9886
    Prev
    Next
    INDEX
    Explanations

    the word "not" and similar negative adverbs and conjunctions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.79
    EDEFAULT
    -0.79
    XtraEditors
    -0.70
    sizeCache
    -0.67
    WireFormatLite
    -0.66
     VIAF
    -0.63
    DockStyle
    -0.63
    drawSprites
    -0.63
    السكان
    -0.60
     Administrativna
    -0.60
    POSITIVE LOGITS
     nahilalakip
    0.51
    ViewFeatures
    0.49
    ردد
    0.43
    ="#"><
    0.42
    íncia
    0.41
     distanciation
    0.40
    inesis
    0.40
    (?:
    0.39
    CppMethod
    0.39
     Jenkins
    0.38
    Activations Density 2.614%

    No Known Activations