© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 801
    Prev
    Next
    INDEX
    Explanations

    the word "stop" in its various forms, sometimes in association with the word "at."

    oai_token-act-pair · gemini-2.0-flash

    stop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AndEndTag
    -0.82
     مشين
    -0.79
     незавершена
    -0.76
    IUrlHelper
    -0.76
    BibitemShut
    -0.69
     <>",
    -0.66
     estekak
    -0.65
     ویکی‌پدیای
    -0.65
    WaitGroup
    -0.65
    athione
    -0.63
    POSITIVE LOGITS
     at
    0.47
    zzano
    0.46
     there
    0.45
    getActiveSheet
    0.44
    ene
    0.43
     Tu
    0.41
     L
    0.41
    在前
    0.41
    L
    0.40
     scom
    0.40
    Activations Density 7.017%

    No Known Activations