© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2315
    Prev
    Next
    INDEX
    Explanations

    instances of the number three, sometimes in conjunction with other related adjectives and nouns

    oai_token-act-pair · gemini-2.0-flash

    three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     
    -0.52
    ,
    -0.50
     .
    -0.48
     He
    -0.45
     an
    -0.44
    бы
    -0.43
     A
    -0.43
     أعلام
    -0.42
     co
    -0.42
     either
    -0.42
    POSITIVE LOGITS
    IntoConstraints
    1.16
    sizeCache
    0.95
     виправивши
    0.86
     onPostExecute
    0.83
    Vidite
    0.83
    contentLoaded
    0.83
     snippetHide
    0.80
     getItemId
    0.80
     initComponents
    0.79
    principalColumn
    0.79
    Activations Density 8.206%

    No Known Activations