© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15327
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives referring to multiple instances of the noun

    oai_token-act-pair · gemini-2.0-flash

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    RetentionPolicy
    -0.68
    AnchorStyles
    -0.55
    Personendaten
    -0.54
     isNameExpr
    -0.54
    eradish
    -0.52
     Италијани
    -0.51
    oglo
    -0.49
    Sucesor
    -0.49
     celui
    -0.48
     مشين
    -0.48
    POSITIVE LOGITS
     Harbour
    0.58
    DispatchToProps
    0.55
    usermodel
    0.54
     harbour
    0.49
    SqlClient
    0.49
     atteinte
    0.47
     oignon
    0.47
    /***/
    0.47
    annique
    0.46
     NSObject
    0.46
    Activations Density 4.623%

    No Known Activations