© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    words related to design, and sometimes words related to medicine or science

    oai_token-act-pair · gemini-2.0-flash

    car/structural descriptions

    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
     colourful
    -0.59
    Colorful
    -0.57
     colorful
    -0.55
     colors
    -0.53
     Colorful
    -0.53
     colours
    -0.51
     coloridos
    -0.49
    colors
    -0.49
     colores
    -0.49
    sunset
    -0.48
    POSITIVE LOGITS
    msgTypes
    0.90
    webElementGuid
    0.74
     surla
    0.74
    MigrationBuilder
    0.72
    IsContent
    0.70
     חיצוניים
    0.70
     TestBed
    0.69
    AnchorStyles
    0.67
    MessageOf
    0.66
    ChildScrollView
    0.66
    Activations Density 5.571%

    No Known Activations