© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6174
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to manufacturing and electronics

    oai_token-act-pair · gemini-2.0-flash

    terms related to functions or purposes

    np_token-act-pair-logits · gpt-4o-mini

    technological development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RegressionTest
    -0.77
    ########.
    -0.75
    URLException
    -0.63
    #+#
    -0.59
    AnchorTagHelper
    -0.59
    脚注の使い方
    -0.59
    ArgsConstructor
    -0.59
    Tetapi
    -0.58
    DataAnnotations
    -0.56
    yntaxException
    -0.56
    POSITIVE LOGITS
     function
    0.54
     content
    0.52
    empl
    0.50
    function
    0.50
    śni
    0.49
     Function
    0.48
     flexible
    0.48
     conversion
    0.47
    Content
    0.47
    Function
    0.46
    Activations Density 9.549%

    No Known Activations