© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4067
    Prev
    Next
    INDEX
    Explanations

    sentences where helping or hindering is discussed

    oai_token-act-pair · gemini-2.0-flash

    help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    IsContent
    -0.69
    Oneof
    -0.67
     postIndex
    -0.66
    didSet
    -0.63
    chaqueta
    -0.59
     Soccerway
    -0.59
     StatefulWidget
    -0.58
     चीज़ों
    -0.57
    ToProps
    -0.57
     Theſe
    -0.57
    POSITIVE LOGITS
     us
    0.86
     him
    0.77
     yourself
    0.66
     them
    0.65
     me
    0.63
    <bos>
    0.62
     you
    0.57
     himself
    0.54
    him
    0.52
     ourselves
    0.51
    Activations Density 0.949%

    No Known Activations