© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9623
    Prev
    Next
    INDEX
    Explanations

    descriptions of an airport project, assessing its value and impact

    oai_token-act-pair · gemini-2.0-flash

    MessageOf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     JpaRepository
    -0.72
    RemoveField
    -0.70
    PointerException
    -0.63
    ControllerTest
    -0.62
     yii
    -0.62
    ExecutorService
    -0.61
    Portale
    -0.58
     CommonModule
    -0.57
     ModelExpression
    -0.57
    BufferedReader
    -0.54
    POSITIVE LOGITS
    MessageOf
    0.69
    GOTREF
    0.54
    WebElementEntity
    0.48
    IndentedString
    0.46
     Cry
    0.45
    ClCompile
    0.45
     Dunlap
    0.44
     ent
    0.44
     mema
    0.43
    uch
    0.43
    Activations Density 4.885%

    No Known Activations