© 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. 9142
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to javascript

    oai_token-act-pair · gemini-2.0-flash

    assignment operator

    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
    DeleteBehavior
    -0.44
    deck
    -0.42
    ob
    -0.40
     stad
    -0.40
    總統
    -0.39
    either
    -0.39
    Personensuche
    -0.39
    ––
    -0.38
     Censo
    -0.38
    พร
    -0.38
    POSITIVE LOGITS
     StatelessWidget
    0.84
    VIAF
    0.75
     lenker
    0.72
    qrstuvwxyz
    0.69
    esModule
    0.69
     AssemblyTitle
    0.68
    tså
    0.63
    ftagPool
    0.63
    AnchorTagHelper
    0.62
    اریخ
    0.61
    Activations Density 0.469%

    No Known Activations