© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13594
    Prev
    Next
    INDEX
    Explanations

    mentions of obstacles or difficulties

    oai_token-act-pair · gemini-2.0-flash

    barrier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.77
     gynhyrchwyd
    -0.61
    IUrlHelper
    -0.56
     guère
    -0.47
    contentLoaded
    -0.45
     CascadeType
    -0.44
    InstrumentedTest
    -0.41
    IVer
    -0.41
     équilibr
    -0.41
     reemplazo
    -0.40
    POSITIVE LOGITS
     obstacle
    0.81
     obstacles
    0.80
     itſelf
    0.80
     impediments
    0.75
    obstacles
    0.74
    obstacle
    0.74
     obstructions
    0.74
     myſelf
    0.73
    koła
    0.73
     barriers
    0.72
    Activations Density 0.871%

    No Known Activations