© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12309
    Prev
    Next
    INDEX
    Explanations

    instances of people speaking (say, tell, etc.) in quotes or other means of indicating speech

    oai_token-act-pair · gemini-2.0-flash

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     say
    -1.77
    Say
    -1.63
     Say
    -1.57
    say
    -1.54
     SAY
    -1.49
     says
    -1.48
    <bos>
    -1.47
     saying
    -1.42
     Says
    -1.41
     Saying
    -1.34
    POSITIVE LOGITS
    انتهای
    0.59
    mobileqq
    0.50
    chyma
    0.49
    veling
    0.48
    queur
    0.48
    ByVersion
    0.48
    ίσ
    0.47
    ICOLON
    0.47
     sounding
    0.45
    ODER
    0.45
    Activations Density 3.738%

    No Known Activations