© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16249
    Prev
    Next
    INDEX
    Explanations

    links to external resources

    oai_token-act-pair · gemini-2.0-flash

    Read/Continue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    تقاوى
    -0.84
     CreateTagHelper
    -0.74
    IUrlHelper
    -0.66
     GenerationType
    -0.65
     MainAxisSize
    -0.63
    exitRule
    -0.61
     Schumer
    -0.59
    tvguidetime
    -0.58
    CDCl
    -0.58
    protoc
    -0.58
    POSITIVE LOGITS
    <bos>
    0.67
     nakalista
    0.54
    *
    0.47
    Former
    0.46
    */].
    0.46
    printLine
    0.45
    former
    0.43
    FloatField
    0.43
     hine
    0.43
    ismic
    0.43
    Activations Density 3.197%

    No Known Activations