© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13394
    Prev
    Next
    INDEX
    Explanations

    Finnish toponyms

    oai_token-act-pair · gemini-2.0-flash

    code/technical language

    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
     समीक्षाओं
    -0.66
    azgo
    -0.65
     alphabetically
    -0.63
     चीज़ों
    -0.62
     verbally
    -0.61
    kloped
    -0.60
    bootstrapcdn
    -0.58
     saites
    -0.56
    pulumi
    -0.56
    logrus
    -0.56
    POSITIVE LOGITS
    makeConstraints
    0.69
    <bos>
    0.50
     const
    0.46
    WriteAttribute
    0.45
     MyBatis
    0.44
     ry
    0.43
     resourceCulture
    0.43
     truth
    0.43
     soi
    0.42
    const
    0.41
    Activations Density 0.725%

    No Known Activations