© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10189
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe the process of evaluating a claim

    oai_token-act-pair · gemini-2.0-flash

    descriptive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    UnknownFields
    -0.62
    ResumeLayout
    -0.60
    EndGlobal
    -0.57
    PostExecute
    -0.56
    atissimo
    -0.56
    nitten
    -0.55
    seigneur
    -0.52
     pulumi
    -0.52
    executeUpdate
    -0.51
    pixabay
    -0.51
    POSITIVE LOGITS
     nicer
    1.13
     faster
    1.12
     fewer
    1.09
     easier
    1.09
     prettier
    1.08
     narrower
    1.07
     hơn
    1.06
    easier
    1.05
     quicker
    1.05
     brighter
    1.05
    Activations Density 1.856%

    No Known Activations