© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4004
    Prev
    Next
    INDEX
    Explanations

    instances of people "saying" or "stating" something

    oai_token-act-pair · gemini-2.0-flash

    saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     saying
    -2.11
    <bos>
    -1.78
    saying
    -1.72
     Saying
    -1.62
    Saying
    -1.45
     stating
    -1.33
     diciendo
    -1.29
     sayin
    -1.26
     telling
    -1.14
     dizendo
    -1.13
    POSITIVE LOGITS
    LabelTagHelper
    0.64
     getRule
    0.63
    EObject
    0.63
    Ỉ
    0.60
    CloseOperation
    0.59
    LayoutConstraint
    0.56
    ecuzione
    0.54
    ciful
    0.53
    arter
    0.52
    licants
    0.52
    Activations Density 0.711%

    No Known Activations