© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10058
    Prev
    Next
    INDEX
    Explanations

    sentences that describe something coming to an end, or a certain time period ending

    oai_token-act-pair · gemini-2.0-flash

    come, reach

    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
    __":
    -0.68
    PDOException
    -0.57
    joso
    -0.56
    XmlAccessorType
    -0.56
    __':
    -0.55
    raded
    -0.50
    HasForeignKey
    -0.49
     Cranston
    -0.48
    neté
    -0.48
    XtraReports
    -0.47
    POSITIVE LOGITS
     come
    1.73
     reach
    1.63
     Reach
    1.61
    Reach
    1.56
     reaching
    1.54
    reach
    1.49
     reached
    1.48
     Reaching
    1.48
     Come
    1.48
     came
    1.44
    Activations Density 2.424%

    No Known Activations