© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    words related to policy and governmental organizations and documents

    oai_token-act-pair · gemini-2.0-flash

    technical or academic terminology

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

    projects and development

    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
    GEBURTSDATUM
    -0.82
    StructEnd
    -0.75
     disambiguazione
    -0.69
     مشين
    -0.69
    AccessorTable
    -0.69
    KURZBESCHREIBUNG
    -0.68
    IsMutable
    -0.68
    //};
    -0.67
    >();
    -0.67
     ProtoMessage
    -0.67
    POSITIVE LOGITS
     autorytatywna
    0.50
    Manbalar
    0.49
    method
    0.44
     дел
    0.43
     PERSPECT
    0.43
     Practice
    0.42
     tege
    0.42
     nevo
    0.41
     taking
    0.41
    semantics
    0.41
    Activations Density 3.984%

    No Known Activations