© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12232
    Prev
    Next
    INDEX
    Explanations

    instances of something increasing or being turned on

    oai_token-act-pair · gemini-2.0-flash

    induced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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>
    -1.65
     induced
    -0.66
     вы
    -0.58
    lay
    -0.56
     Induced
    -0.50
    '
    -0.50
    induced
    -0.50
     between
    -0.49
    Between
    -0.48
    Induced
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.94
     HasFactory
    0.71
     Roskov
    0.69
    ConstraintMaker
    0.65
     BorderSide
    0.64
    protoimpl
    0.62
    InjectAttribute
    0.62
     CURLOPT
    0.62
    ">*</
    0.61
     testSet
    0.60
    Activations Density 0.991%

    No Known Activations