© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9207
    Prev
    Next
    INDEX
    Explanations

    instances of the word "not" preceded by a person

    oai_token-act-pair · gemini-2.0-flash

    programming and technical terminology

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

    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_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
    المكان
    -0.71
     leſs
    -0.68
     ModelExpression
    -0.62
     समीक्षक
    -0.60
     photolibrary
    -0.59
    Lähteet
    -0.59
    inghouse
    -0.58
    Atsauces
    -0.58
     Houſe
    -0.57
    lessness
    -0.57
    POSITIVE LOGITS
    tagHelper
    0.50
     onAnimation
    0.50
     Seit
    0.45
     necessarily
    0.44
     soddis
    0.44
    MergeFrom
    0.43
     Chwiliwch
    0.43
    IVEREF
    0.43
     StatelessWidget
    0.42
     fiducia
    0.41
    Activations Density 1.216%

    No Known Activations