© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13702
    Prev
    Next
    INDEX
    Explanations

    words that are structural to questions as well as question marks, "to" and "that."

    oai_token-act-pair · gemini-2.0-flash

    Defining words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     actuación
    -0.38
    omnia
    -0.36
     része
    -0.36
     liknande
    -0.35
     allmän
    -0.35
    eseorang
    -0.35
     usarlo
    -0.35
     early
    -0.34
    BQ
    -0.34
    miljø
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     noqa
    0.70
    ioutil
    0.68
    OGND
    0.68
    webElement
    0.68
    <bos>
    0.68
    oa̍t
    0.67
     nahilalakip
    0.65
     wireType
    0.64
    Vidite
    0.64
    Activations Density 12.815%

    No Known Activations