© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4902
    Prev
    Next
    INDEX
    Explanations

    technical or scientific passages, especially those with citations or that draw conclusions.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     الاطلاع
    -0.77
     betweenstory
    -0.76
    /*
    -0.74
    )");
    -0.73
     AssemblyTitle
    -0.72
    хьтан
    -0.69
     typelib
    -0.69
    ulemon
    -0.68
     AssemblyCompany
    -0.68
    orsese
    -0.67
    POSITIVE LOGITS
     eens
    0.39
     dilihat
    0.39
    <bos>
    0.39
     kaynak
    0.39
     As
    0.39
     perchè
    0.38
     ‘
    0.37
    şem
    0.36
     omdat
    0.36
    getBy
    0.35
    Activations Density 2.524%

    No Known Activations