© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9054
    Prev
    Next
    INDEX
    Explanations

    a mix of terms about programming code, cell development and football, possibly related to statistical data

    oai_token-act-pair · gemini-2.0-flash

    Code and scientific descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    eleste
    -0.50
    GEBURTS
    -0.49
    RegistryLite
    -0.49
    Otras
    -0.47
     <<<<<<<<<<<<<<
    -0.47
    ('.')
    -0.47
    taine
    -0.46
     оригіналу
    -0.46
    iron
    -0.45
    TAIN
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.67
     ddelweddau
    0.64
    urably
    0.62
     NgModule
    0.57
     Référence
    0.54
     Cato
    0.54
    }{*}{}
    0.52
    Література
    0.52
    ScopeManager
    0.51
    webElementXpaths
    0.51
    Activations Density 4.491%

    No Known Activations