© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10922
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to reaching a broad audience

    oai_token-act-pair · gemini-2.0-flash

    reaching an audience

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Audience
    -1.70
     audience
    -1.66
    Audience
    -1.63
    audience
    -1.51
     audiences
    -1.41
    Audiences
    -1.26
     crowd
    -1.08
     Publikum
    -1.05
     audiencia
    -1.02
     crowds
    -0.93
    POSITIVE LOGITS
    RegressionTest
    0.62
    ManagedBean
    0.57
    setVerticalGroup
    0.57
    principalColumn
    0.54
    netbeans
    0.52
    TagMode
    0.50
     Quince
    0.50
    rzost
    0.50
    Šaltiniai
    0.50
    blom
    0.49
    Activations Density 3.467%

    No Known Activations