© 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. 6520
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    `\[`

    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
     up
    -0.77
    Up
    -0.60
    up
    -0.56
     Up
    -0.53
    アップ
    -0.48
    htdocs
    -0.48
     Normdatei
    -0.46
    UP
    -0.46
     UP
    -0.45
    ingo
    -0.43
    POSITIVE LOGITS
     handker
    0.69
    numerusform
    0.68
    UnusedPrivate
    0.65
     handkerchief
    0.63
     pardon
    0.62
     LoggerFactory
    0.61
    rentices
    0.60
     springfox
    0.60
     kcal
    0.60
    EndInit
    0.60
    Activations Density 0.057%

    No Known Activations