© 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. 10453
    Prev
    Next
    INDEX
    Explanations

    SQL code and related keywords

    oai_token-act-pair · gemini-2.0-flash

    JOIN

    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
     itſelf
    -1.20
     pleaſure
    -1.13
     myſelf
    -1.10
     Monfieur
    -1.06
     againſt
    -1.00
     raiſ
    -0.99
     themſelves
    -0.99
     poffible
    -0.98
     ſtate
    -0.96
     fubject
    -0.95
    POSITIVE LOGITS
    prepareStatement
    0.81
     Sequelize
    0.72
    cshtml
    0.66
     ActionResult
    0.66
    antMatchers
    0.65
     SqlCommand
    0.63
    Javadoc
    0.60
    ibatis
    0.59
    featureID
    0.59
    knex
    0.59
    Activations Density 1.921%

    No Known Activations