© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10668
    Prev
    Next
    INDEX
    Explanations

    words and symbols used in diagrams and to refer to parts of them

    oai_token-act-pair · gemini-2.0-flash

    diagrams and annotations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Portale
    -0.65
    KommentareTeilen
    -0.65
    LikeLike
    -0.56
    obie
    -0.50
    NullException
    -0.50
    complexContent
    -0.49
     GenerationType
    -0.46
    ime
    -0.45
     SearchView
    -0.45
    <thead>
    -0.44
    POSITIVE LOGITS
    saraba
    0.81
     labels
    0.73
    AndEndTag
    0.69
     LABEL
    0.68
     label
    0.68
     Label
    0.62
     Labels
    0.61
    DJANGO
    0.61
    indic
    0.60
     Indic
    0.60
    Activations Density 3.479%

    No Known Activations