© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16240
    Prev
    Next
    INDEX
    Explanations

    words related to journalism and also the word woodpecker and phrases about women

    oai_token-act-pair · gemini-2.0-flash

    news reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    UnsafeEnabled
    -0.82
     تضيفلها
    -0.69
    VIAF
    -0.68
    TagMode
    -0.67
    AccessorTable
    -0.65
    Zeneca
    -0.65
    __).
    -0.64
     ujednoznacz
    -0.63
     podjela
    -0.63
    󠁢
    -0.62
    POSITIVE LOGITS
    WriteLiteral
    0.66
     initComponents
    0.54
     Zone
    0.50
     zone
    0.48
    Результа
    0.42
    OTH
    0.41
     better
    0.41
    kkit
    0.40
     us
    0.40
    EndContext
    0.40
    Activations Density 2.840%

    No Known Activations