© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12125
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" and negations of the word "not"

    oai_token-act-pair · gemini-2.0-flash

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     виправивши
    -1.22
    BibitemShut
    -1.09
     مشين
    -1.05
    parsedMessage
    -1.03
     itſelf
    -1.01
     незавершена
    -1.00
    Personensuche
    -0.99
    Autoritní
    -0.99
     purpoſe
    -0.99
     houſe
    -0.98
    POSITIVE LOGITS
    '
    0.66
    !
    0.65
    #
    0.62
     envisaged
    0.60
    h
    0.59
    H
    0.56
    D
    0.55
    `
    0.53
    v
    0.53
     :
    0.53
    Activations Density 0.544%

    No Known Activations