Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14683
    Prev
    Next
    INDEX
    Explanations

    words or short phrases expressing cause and effect or relationships.

    oai_token-act-pair · gemini-2.0-flash

    complex descriptions

    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
    QMetaType
    -0.59
    ThroughAttribute
    -0.56
    AndEndTag
    -0.56
    providedIn
    -0.52
    GEBURTS
    -0.52
     zorgt
    -0.51
    EDEFAULT
    -0.50
     BIBSYS
    -0.47
    protoc
    -0.45
    发表于
    -0.45
    POSITIVE LOGITS
     having
    0.82
    having
    0.73
     being
    0.73
    crapers
    0.71
     HAVING
    0.67
     reserving
    0.66
     treating
    0.66
     letting
    0.65
    ematic
    0.63
    pears
    0.63
    Activations Density 4.703%

    No Known Activations