© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12385
    Prev
    Next
    INDEX
    Explanations

    lines of code in C

    oai_token-act-pair · gemini-2.0-flash

    coding constants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    脚注の使い方
    -0.81
                  
    -0.77
     تضيفلها
    -0.75
    .*")]
    -0.72
    providedIn
    -0.67
                 
    -0.66
    bootstrapcdn
    -0.64
     contextLoads
    -0.63
     CreateTagHelper
    -0.61
    !(:
    -0.61
    POSITIVE LOGITS
    <?
    0.63
    setVerticalGroup
    0.57
    <bos>
    0.52
     dramatique
    0.51
    titem
    0.50
     åp
    0.49
     ramai
    0.46
     bross
    0.46
     aktive
    0.44
     vocale
    0.44
    Activations Density 0.294%

    No Known Activations