© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16043
    Prev
    Next
    INDEX
    Explanations

    conversational snippets with questions and answers

    oai_token-act-pair · gemini-2.0-flash

    you, are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    rungsseite
    -0.71
     kasarigan
    -0.59
    Mutagenicity
    -0.59
    
    -0.59
    $_['
    -0.58
    دانشنامهٔ
    -0.55
    ppsala
    -0.54
    <bos>
    -0.54
    
    -0.50
     ско
    -0.49
    POSITIVE LOGITS
     Shakspeare
    0.64
     Cæsar
    0.63
     Byz
    0.63
     Koran
    0.60
     quæ
    0.60
     noastre
    0.58
     $_"
    0.58
     Aristotle
    0.57
     Athenians
    0.56
     auricular
    0.56
    Activations Density 3.467%

    No Known Activations