© 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. 10482
    Prev
    Next
    INDEX
    Explanations

    words/phrases of general helpfulness (e.g. public) along with other general topics ranging across work/food/nature

    oai_token-act-pair · gemini-2.0-flash

    supply

    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
    trique
    -0.51
    INGE
    -0.49
    IndexOf
    -0.47
    autique
    -0.45
    indd
    -0.44
    itoria
    -0.43
     صفح
    -0.43
    <bos>
    -0.43
    NodeId
    -0.42
    AVA
    -0.42
    POSITIVE LOGITS
     supply
    1.78
    supply
    1.59
     Supply
    1.52
    Supply
    1.52
     SUPPLY
    1.43
    SUPPLY
    1.14
    upply
    0.95
     brand
    0.94
     crop
    0.84
    brand
    0.81
    Activations Density 8.002%

    No Known Activations