© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 271
    Prev
    Next
    INDEX
    Explanations

    technical details including units of measure, temperatures, and process-related verbs.

    oai_token-act-pair · gemini-2.0-flash

    Cooking and speed measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    mybatisplus
    -0.85
    gården
    -0.67
    <bos>
    -0.66
    parian
    -0.54
    multer
    -0.52
    tocin
    -0.51
    LOGOUT
    -0.51
     chắn
    -0.50
    SVM
    -0.49
     comen
    -0.49
    POSITIVE LOGITS
     وتسجيلات
    0.73
    MemoryWarning
    0.69
     raiſ
    0.68
    abestanden
    0.66
    KommentareTeilen
    0.65
     Reſ
    0.64
     Theſe
    0.63
    Geplaatst
    0.60
     fevere
    0.59
     Diſ
    0.59
    Activations Density 1.106%

    No Known Activations