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. 10227
    Prev
    Next
    INDEX
    Explanations

    varied, but seems to be looking for specific constructions involving "this", offers for services, and the word "profit".

    oai_token-act-pair · gemini-2.0-flash

    "thus" or "way"

    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
     accounts
    -0.47
    tula
    -0.40
    midt
    -0.40
    ỏ
    -0.39
     Bro
    -0.38
    wid
    -0.38
    tiana
    -0.38
    ijne
    -0.37
     tor
    -0.37
    tul
    -0.36
    POSITIVE LOGITS
     así
    1.38
     così
    1.29
     way
    1.28
     näin
    1.27
     ainsi
    1.21
     így
    1.21
     assim
    1.19
     thus
    1.18
    thus
    1.12
     Böyle
    1.06
    Activations Density 1.431%

    No Known Activations