© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13639
    Prev
    Next
    INDEX
    Explanations

    proper nouns or brand names related to technical subjects, for example, medicine, programming or physics

    oai_token-act-pair · gemini-2.0-flash

    Code/software references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     ModelExpression
    -0.91
     للاسماء
    -0.82
    UnusedPrivate
    -0.71
    DockStyle
    -0.68
     CreateTagHelper
    -0.67
    writeFieldEnd
    -0.66
    WebElementEntity
    -0.64
     propOrder
    -0.63
     protoimpl
    -0.63
     링크
    -0.62
    POSITIVE LOGITS
     standard
    0.48
     introduced
    0.46
    дии
    0.45
     included
    0.44
    igten
    0.43
    Field
    0.43
    introduced
    0.43
    atorul
    0.43
     daly
    0.42
    și
    0.42
    Activations Density 6.957%

    No Known Activations