© 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. 4586
    Prev
    Next
    INDEX
    Explanations

    phrases including "the" followed by a word starting with "th", the word "slight", and references to being physically fit.

    oai_token-act-pair · 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
     the
    -1.34
     poslední
    -0.57
    Javadoc
    -0.54
     самое
    -0.52
    Клуб
    -0.51
    NÍ
    -0.51
    tothe
    -0.50
    the
    -0.50
     οι
    -0.50
    },[])
    -0.49
    POSITIVE LOGITS
    SpringBootTest
    0.77
    UrlResolution
    0.66
    reactstrap
    0.59
    WebVitals
    0.56
    IMPORTED
    0.56
    RegressionTest
    0.55
    TemporalType
    0.55
    //
    0.55
    StreetMap
    0.54
    imetsu
    0.54
    Activations Density 1.083%

    No Known Activations