© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11125
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

    oai_token-act-pair · gemini-2.0-flash

    error bars and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     makeStyles
    -0.54
    addGap
    -0.53
    RetentionPolicy
    -0.50
     Divulgação
    -0.48
    CompoundButton
    -0.45
    GraphicsUnit
    -0.45
    DataAnnotations
    -0.45
    OGND
    -0.44
    انه
    -0.44
    rifuge
    -0.43
    POSITIVE LOGITS
    SourceChecksum
    0.81
    Diweddarwch
    0.63
    InjectAttribute
    0.61
    SharedCtor
    0.59
    rostis
    0.57
    RegressionTest
    0.57
     ChromeDriver
    0.56
     виправивши
    0.55
    новниш
    0.53
     AssemblyTitle
    0.53
    Activations Density 12.049%

    No Known Activations