© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15108
    Prev
    Next
    INDEX
    Explanations

    words related to computer and legal terminology, and foreign language terms

    oai_token-act-pair · gemini-2.0-flash

    code/non-English

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ness
    -0.82
    ם
    -0.75
    nya
    -0.59
    ochrom
    -0.57
     ein
    -0.53
     barro
    -0.52
     geolog
    -0.51
     seda
    -0.50
     Obrador
    -0.50
     conduc
    -0.50
    POSITIVE LOGITS
     nahilalakip
    0.96
     Merri
    0.94
    ri
    0.91
     SSI
    0.89
     CCI
    0.88
    DotNetBar
    0.87
    __":
    0.84
    atti
    0.84
     PPI
    0.83
     MCI
    0.83
    Activations Density 3.525%

    No Known Activations