© 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. 3566
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    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
    fclose
    -0.41
    ):=\
    -0.40
    viewpager
    -0.38
     thine
    -0.37
    atop
    -0.37
     AssemblyProduct
    -0.37
    </tfoot>
    -0.36
    ніципалі
    -0.36
     domestic
    -0.36
    []=
    -0.36
    POSITIVE LOGITS
    ništ
    0.76
     ostavi
    0.71
    expandindo
    0.67
    цездатний
    0.66
    TagMode
    0.66
    Diweddarwch
    0.65
     beginnetje
    0.63
     purpoſe
    0.62
     виправивши
    0.61
     uſed
    0.61
    Activations Density 0.377%

    No Known Activations