© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3432
    Prev
    Next
    INDEX
    Explanations

    statistical measures and formulas

    oai_token-act-pair · gemini-2.0-flash

    multiplication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WaitGroup
    -0.74
    MessageDigest
    -0.69
     resourceCulture
    -0.69
    waitKey
    -0.67
    HomeAsUpEnabled
    -0.66
    ImageIO
    -0.63
    ąt
    -0.61
    ioutil
    -0.60
    KommentareTeilen
    -0.60
     StatelessWidget
    -0.59
    POSITIVE LOGITS
     multiple
    1.31
    multi
    1.24
     multi
    1.24
     times
    1.20
    multiple
    1.20
    Multiple
    1.16
    Multi
    1.13
     Multiple
    1.13
     Multi
    1.08
     MULTIPLE
    1.02
    Activations Density 2.857%

    No Known Activations