© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5775
    Prev
    Next
    INDEX
    Explanations

    the word 'you' and other second-person pronouns

    oai_token-act-pair · gemini-2.0-flash

    Coupon codes and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     gemens
    -0.47
     chrétiens
    -0.46
     võimal
    -0.44
     svårt
    -0.43
     AssemblyCulture
    -0.42
     médié
    -0.40
     spē
    -0.40
     graphique
    -0.38
    fileType
    -0.38
     graphiques
    -0.37
    POSITIVE LOGITS
    WebVitals
    0.85
     nahilalakip
    0.82
     Biôgrafia
    0.77
    openzeppelin
    0.69
    XmlAccessType
    0.69
    SourceChecksum
    0.67
    AlterField
    0.67
    prnewswire
    0.65
    jfree
    0.65
     NSCoder
    0.65
    Activations Density 0.923%

    No Known Activations