© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6517
    Prev
    Next
    INDEX
    Explanations

    sections of Java code declaring static final integer constants.

    oai_token-act-pair · gemini-2.0-flash

    static

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     GenerationType
    -1.21
    Jeografia
    -1.00
     protoimpl
    -0.99
     propOrder
    -0.96
     Efq
    -0.95
    MENAFN
    -0.94
    TagMode
    -0.94
    complexContent
    -0.93
    principalTable
    -0.92
    =$?
    -0.92
    POSITIVE LOGITS
     finish
    0.46
     her
    0.45
     fini
    0.45
     послед
    0.45
     finally
    0.44
    末
    0.43
     “
    0.42
     no
    0.42
     finishes
    0.41
     s
    0.41
    Activations Density 0.053%

    No Known Activations