© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4016
    Prev
    Next
    INDEX
    Explanations

    words related to sewing and fabrics, also some common small words

    oai_token-act-pair · gemini-2.0-flash

    fabrics and clothes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    routeProvider
    -0.68
     насељу
    -0.68
    ViewImports
    -0.68
    awaiter
    -0.67
     ExecuteAsync
    -0.63
     ویکی‌پدیای
    -0.61
    RenderAtEndOf
    -0.60
    fjspx
    -0.60
    tagHelperRunner
    -0.59
     Biôgrafia
    -0.59
    POSITIVE LOGITS
    ésultat
    0.57
     cups
    0.48
     Taus
    0.47
    Clik
    0.47
    Portail
    0.45
    ayon
    0.43
    ripple
    0.42
    étés
    0.42
     Tapes
    0.42
     undi
    0.41
    Activations Density 3.702%

    No Known Activations