© 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. 11924
    Prev
    Next
    INDEX
    Explanations

    descriptions of household interiors

    oai_token-act-pair · gemini-2.0-flash

    Web code

    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
    ruptedException
    -0.58
     solares
    -0.45
     Übersetzung
    -0.45
     pylint
    -0.44
     excus
    -0.44
     traduce
    -0.43
     traduit
    -0.43
     Societies
    -0.42
    <tbody>
    -0.42
     históricas
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.84
     Wikimedijinoj
    0.79
    Tembelea
    0.71
    transQ
    0.70
     disambiguazione
    0.68
     mono
    0.66
     CreateTagHelper
    0.64
    mono
    0.64
    windowFixed
    0.64
    Дереккөздер
    0.63
    Activations Density 0.339%

    No Known Activations