© 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. 14693
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gemini-2.0-flash

    names of people

    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
    stdc
    -0.68
    Gön
    -0.66
    BeginContext
    -0.63
    ConstraintMaker
    -0.60
     BitmapFactory
    -0.57
    buttonShape
    -0.57
    DataAnnotations
    -0.57
     considérons
    -0.54
    reportWebVitals
    -0.54
    SequentialGroup
    -0.53
    POSITIVE LOGITS
    <bos>
    0.98
     kasarigan
    0.67
    Toolbox
    0.51
    حياتها
    0.47
     facing
    0.45
    هرست
    0.45
     sor
    0.43
    付き合い
    0.43
    verwijspagina
    0.43
    demment
    0.43
    Activations Density 3.112%

    No Known Activations