© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5095
    Prev
    Next
    INDEX
    Explanations

    words and phrases from disparate subjects including personal stories, calculation results, and biology.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    WebVitals
    -0.87
    bootstrapcdn
    -0.86
    AndEndTag
    -0.82
    AccessorTable
    -0.82
     defaultstate
    -0.81
    出版年
    -0.77
    VYMaps
    -0.75
    хьтан
    -0.72
    tagHelperRunner
    -0.71
    glEnd
    -0.71
    POSITIVE LOGITS
    Dichloroethane
    0.36
    มากกว่า
    0.33
    InstanceState
    0.32
    াস
    0.31
    InsertCommand
    0.30
    Pipe
    0.30
    thest
    0.30
    zimy
    0.30
    Hearing
    0.29
    gether
    0.29
    Activations Density 9.111%

    No Known Activations