© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15035
    Prev
    Next
    INDEX
    Explanations

    negations, especially "not."

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    出版年
    -0.96
     فريبيس
    -0.85
    MigrationBuilder
    -0.81
    ftagPool
    -0.78
    antMatchers
    -0.78
     समीक्षक
    -0.77
     NSCoder
    -0.76
    ValueStyle
    -0.74
    Geplaatst
    -0.72
    GEBURTSDATUM
    -0.72
    POSITIVE LOGITS
     an
    0.61
     the
    0.45
     hyperbolic
    0.44
     a
    0.44
     helping
    0.44
    <bos>
    0.44
     something
    0.41
     mencu
    0.41
     working
    0.40
     g
    0.40
    Activations Density 0.192%

    No Known Activations