© 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. 14672
    Prev
    Next
    INDEX
    Explanations

    code snippets and questions related to programming

    oai_token-act-pair · gemini-2.0-flash

    Programming code

    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
    <bos>
    -0.76
     ostavi
    -0.65
    ,:);
    -0.62
     <=",
    -0.60
     kaarangay
    -0.59
    ,:),
    -0.58
     الحره
    -0.56
    Tazama
    -0.55
     internetowa
    -0.52
     ""],
    -0.51
    POSITIVE LOGITS
     Kellogg
    0.56
     Exactos
    0.55
     Granville
    0.54
     Sodom
    0.54
     FontWeight
    0.52
     pamp
    0.52
     Chá
    0.51
     Cedric
    0.50
     HasFactory
    0.50
    enst
    0.50
    Activations Density 3.950%

    No Known Activations