© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9850
    Prev
    Next
    INDEX
    Explanations

    adverts/plugs for social media accounts

    oai_token-act-pair · gemini-2.0-flash

    social media engagement

    np_token-act-pair-logits · gpt-4o-mini

    social media links

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     AssemblyCulture
    -0.69
    ]--;
    -0.62
    مقاله
    -0.58
    ]='\
    -0.58
    GraphicsUnit
    -0.57
    Референце
    -0.54
    createTextNode
    -0.54
    niająca
    -0.54
    yntaxException
    -0.54
    ClCompile
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.62
    MigrationBuilder
    0.60
    mpto
    0.51
    KommentareTeilen
    0.50
     encarga
    0.49
    HtmlAttribute
    0.48
    ValueStyle
    0.48
     asegur
    0.47
     Instagram
    0.47
     cérami
    0.46
    Activations Density 1.582%

    No Known Activations