© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11074
    Prev
    Next
    INDEX
    Explanations

    a combination of mathematical symbols, reference symbols and historical events

    oai_token-act-pair · gemini-2.0-flash

    cdot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     deaktiviert
    -0.45
     equivalent
    -0.44
    rededor
    -0.43
    SpringBootTest
    -0.42
    ecto
    -0.42
    XmlAttribute
    -0.41
     Integr
    -0.41
     land
    -0.41
    誼
    -0.41
     Integration
    -0.40
    POSITIVE LOGITS
    Personendaten
    0.75
    enumii
    0.74
     nakalista
    0.67
    AddTagHelper
    0.66
     resourceCulture
    0.63
    AlterField
    0.61
    bewerken
    0.59
    )";
    0.59
    Tikang
    0.59
    存于互联网档案馆
    0.58
    Activations Density 6.565%

    No Known Activations