© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14399
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in formal legal and political writing

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    complexContent
    -0.54
    IVEREF
    -0.51
    Blick
    -0.49
    QMetaType
    -0.47
    Portail
    -0.47
     tartalomajánló
    -0.44
    MockMvc
    -0.44
     ***!
    -0.44
    Välislingid
    -0.43
    ServiceModel
    -0.43
    POSITIVE LOGITS
     ferons
    0.68
     يتيمه
    0.66
     disponibilités
    0.64
    OGND
    0.58
    GEBURTSDATUM
    0.58
     stratégique
    0.57
    WebVitals
    0.55
     popoli
    0.54
    actéristique
    0.53
    tableFuture
    0.53
    Activations Density 1.662%

    No Known Activations