© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11700
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to HTML tags or the end of lines

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     houſe
    -0.88
    RegressionTest
    -0.88
    Portail
    -0.88
     utafitiHapana
    -0.88
    webElementXpaths
    -0.85
     EconPapers
    -0.85
     AssemblyCulture
    -0.85
    __*/
    -0.84
     незавершена
    -0.84
    expandindo
    -0.82
    POSITIVE LOGITS
     r
    0.47
    h
    0.44
     s
    0.43
     h
    0.43
     b
    0.43
     l
    0.42
     الدرا
    0.42
     B
    0.41
     I
    0.40
     t
    0.40
    Activations Density 1.807%

    No Known Activations