© 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. 15915
    Prev
    Next
    INDEX
    Explanations

    commas that are close to certain function words.

    oai_token-act-pair · gemini-2.0-flash

    Stopwords/punctuation

    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
    IsContent
    -0.66
     larmes
    -0.59
     /\.(
    -0.58
    aronder
    -0.57
    SPECTION
    -0.56
    chiali
    -0.56
    horabuena
    -0.56
     Whereas
    -0.55
    Уважаемые
    -0.55
    odynamic
    -0.54
    POSITIVE LOGITS
     tartalomajánló
    0.61
    )]
    0.61
    Демографія
    0.57
    ScopeManager
    0.57
    >*/
    0.56
     kasarigan
    0.54
    UnusedPrivate
    0.53
    XmlEnum
    0.51
     propOrder
    0.51
    onActivityResult
    0.50
    Activations Density 3.613%

    No Known Activations