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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10257
    Prev
    Next
    INDEX
    Explanations

    the word "it" and words associated with time

    oai_token-act-pair · gemini-2.0-flash

    General unstructured text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ås
    -0.50
    JspWriter
    -0.47
    ernes
    -0.46
     aves
    -0.44
    REZ
    -0.43
    CreateModel
    -0.43
    jam
    -0.42
    ์
    -0.42
     Denn
    -0.42
     Jaw
    -0.42
    POSITIVE LOGITS
     '\\;'
    0.79
    ItemBackground
    0.79
    awtextra
    0.74
    PageFactory
    0.66
    Obrázky
    0.63
     Exacts
    0.60
    fastjson
    0.60
     Meksiku
    0.59
    SerializedName
    0.59
    AddTagHelper
    0.59
    Activations Density 0.653%

    No Known Activations