© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15770
    Prev
    Next
    INDEX
    Explanations

    code with decimals, the keyword "on", and the 'subscribe' function

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    akterysty
    -0.53
    <thead>
    -0.53
    ReusableCell
    -0.51
     CreateTagHelper
    -0.50
     relâche
    -0.49
     gezet
    -0.49
    لينكات
    -0.47
    BeginInit
    -0.47
    poque
    -0.47
    IContainer
    -0.47
    POSITIVE LOGITS
    enumi
    0.82
     Cielo
    0.56
    //
    0.53
    Ӕ
    0.53
     sequentially
    0.52
    KURZBESCHREIBUNG
    0.51
     Saj
    0.51
    cibly
    0.49
    odacty
    0.49
     Sequential
    0.49
    Activations Density 1.347%

    No Known Activations