© 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. 15144
    Prev
    Next
    INDEX
    Explanations

    qualifying words or phrases and interjections

    oai_token-act-pair · gemini-2.0-flash

    affirmation

    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
     للمعارف
    -0.79
    adaptiveStyles
    -0.78
    batore
    -0.70
     okuyayım
    -0.69
     الحره
    -0.67
    fromnode
    -0.66
     Proprietary
    -0.64
     stripper
    -0.63
     salu
    -0.62
    InstrumentedTest
    -0.62
    POSITIVE LOGITS
     person
    0.59
    <bos>
    0.54
     all
    0.52
     he
    0.50
    addCriterion
    0.48
     
    0.47
    washingtonpost
    0.47
     they
    0.45
    roduction
    0.45
     pro
    0.44
    Activations Density 6.351%

    No Known Activations