© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9877
    Prev
    Next
    INDEX
    Explanations

    instances of "sh" followed by other characters, likely as part of a gene ID or surname

    oai_token-act-pair · gemini-2.0-flash

    sh

    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
    Negative Logits
     Sh
    -2.38
     sh
    -2.25
    Sh
    -2.22
    sh
    -1.98
     SH
    -1.70
    SH
    -1.63
    <bos>
    -0.96
     Ш
    -0.93
    Shan
    -0.92
     Sha
    -0.92
    POSITIVE LOGITS
     MessageBoxIcon
    0.72
    principalTable
    0.70
    OGND
    0.69
     FontWeight
    0.68
     IConfiguration
    0.67
    DeleteBehavior
    0.66
    WebElementEntity
    0.66
     Roskov
    0.65
    webElementXpaths
    0.62
     AssertionError
    0.62
    Activations Density 0.519%

    No Known Activations