© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11024
    Prev
    Next
    INDEX
    Explanations

    the word "as" followed by other words and punctuation

    oai_token-act-pair · gemini-2.0-flash

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    uxxxx
    -0.68
     незавершена
    -0.66
    PreferredItem
    -0.60
    matchCondition
    -0.57
    Chham
    -0.56
    /**
    -0.55
     bicchiere
    -0.54
     становника
    -0.54
    LLocation
    -0.54
    ollectionView
    -0.52
    POSITIVE LOGITS
     more
    0.59
     even
    0.52
     soon
    0.51
    ListItemIcon
    0.50
    freunde
    0.49
    Threats
    0.49
    InputType
    0.48
     threats
    0.47
    ValueGenerated
    0.47
    outs
    0.47
    Activations Density 0.807%

    No Known Activations