© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5404
    Prev
    Next
    INDEX
    Explanations

    words that are often found at the end of clauses or sentences, indicating a pause or completion of a thought

    oai_token-act-pair · gemini-2.0-flash

    commas/dashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    (
    -0.79
    —
    -0.72
     –
    -0.67
    -
    -0.65
    --
    -0.62
     -
    -0.60
    —(
    -0.57
    )
    -0.53
    [
    -0.53
    ​—
    -0.52
    POSITIVE LOGITS
     Савезне
    0.98
    Personensuche
    0.90
     transfieras
    0.89
    "];
    0.82
     Мексичка
    0.81
    rungsseite
    0.81
    (!__
    0.80
    GEBURTSDATUM
    0.80
     CreateTagHelper
    0.79
    ".
    0.77
    Activations Density 22.438%

    No Known Activations