© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13149
    Prev
    Next
    INDEX
    Explanations

    last names with only one capital letter

    oai_token-act-pair · gemini-2.0-flash

    Scientific paper references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    mapStateToProps
    -0.59
    خواندن
    -0.51
    Conclusiones
    -0.50
    gnation
    -0.50
    citos
    -0.50
    CONCLUSIONES
    -0.48
    UpDown
    -0.48
    ="">
    -0.48
     ")
    -0.47
    "),
    -0.47
    POSITIVE LOGITS
    Kjelder
    0.71
    Portail
    0.68
     ujednoznacz
    0.58
     ModelExpression
    0.57
    IndentedString
    0.56
     JpaRepository
    0.54
     kasarigan
    0.52
    PyErr
    0.52
     intptr
    0.51
    rungsseite
    0.51
    Activations Density 0.710%

    No Known Activations