© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8336
    Prev
    Next
    INDEX
    Explanations

    snippets of code and mathematical equations.

    oai_token-act-pair · gemini-2.0-flash

    mathematical variables and code

    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
    ScopeManager
    -0.73
    MigrationBuilder
    -0.65
     Projektu
    -0.64
     Jacobi
    -0.63
     throats
    -0.63
     tdci
    -0.62
     Rohan
    -0.59
     BSEB
    -0.59
     feroit
    -0.58
     skeletons
    -0.57
    POSITIVE LOGITS
    __':
    0.59
    Сюжет
    0.49
    cia
    0.48
    ład
    0.47
    ьа
    0.47
    ajiban
    0.47
     Science
    0.46
    nonatomic
    0.45
     ""],
    0.45
    __':
    0.45
    Activations Density 2.481%

    No Known Activations