© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5064
    Prev
    Next
    INDEX
    Explanations

    the word "intention" or instances of 'hard work'

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ſelf
    -0.83
    ably
    -0.79
     ſmall
    -0.73
     purpoſe
    -0.71
    hésite
    -0.67
     basic
    -0.67
    tedly
    -0.66
    rova
    -0.65
     iconFacebook
    -0.65
     Theſe
    -0.64
    POSITIVE LOGITS
     DBNull
    0.81
     surla
    0.72
    +#+#
    0.70
    WithIOException
    0.69
    XmlAccessType
    0.69
    tomcat
    0.66
     formé
    0.66
    argout
    0.66
    DoubleQuotes
    0.65
    IntoConstraints
    0.64
    Activations Density 1.425%

    No Known Activations