© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10511
    Prev
    Next
    INDEX
    Explanations

    the prefix "ir" indicating negation

    oai_token-act-pair · gemini-2.0-flash

    the prefix 'ir'

    np_token-act-pair-logits · gpt-4o-mini

    ir

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     الحره
    -0.82
    esModule
    -0.80
    XmlAccessType
    -0.67
     समीक्षक
    -0.64
    EnableWeb
    -0.62
    RepeatedField
    -0.61
    WriteAttribute
    -0.61
     ModelExpression
    -0.59
     CommonModule
    -0.59
     ***!
    -0.58
    POSITIVE LOGITS
     relever
    0.51
     ramai
    0.50
    öst
    0.48
    WithMany
    0.48
     đợi
    0.47
    binaan
    0.47
    äuser
    0.45
    agisse
    0.45
     vänt
    0.44
     referenties
    0.44
    Activations Density 0.276%

    No Known Activations