Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14885
    Prev
    Next
    INDEX
    Explanations

    LEGO product lines, especially the "Mindstorms" and "Technic" lines, and the building components of the Technic line.

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
     оригіналу
    -0.64
    DataAnnotations
    -0.58
    createCell
    -0.55
     Finlande
    -0.55
     Jews
    -0.54
    featureID
    -0.53
    juvant
    -0.53
    lgica
    -0.53
     فريبيس
    -0.52
     Italians
    -0.52
    POSITIVE LOGITS
    argout
    0.55
    AndEndTag
    0.52
     Réponses
    0.52
     resourceCulture
    0.48
     &___
    0.46
    WriteLiteral
    0.45
    Hozzáférés
    0.45
    DMETHOD
    0.43
    Referències
    0.43
     Roskov
    0.43
    Activations Density 0.894%

    No Known Activations