© 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. 13003
    Prev
    Next
    INDEX
    Explanations

    objective-c code/syntax, version control comments, and email application names

    oai_token-act-pair · gemini-2.0-flash

    Lula

    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
    :
    -0.52
    <eos>
    -0.49
    is
    -0.47
    ↵↵
    -0.45
     :
    -0.39
    dr
    -0.39
    "
    -0.38
    Page
    -0.37
     .
    -0.37
    knex
    -0.36
    POSITIVE LOGITS
    Personensuche
    1.16
    Personendaten
    0.95
     ModelExpression
    0.94
     ProtoMessage
    0.93
     Normdatei
    0.90
    MarshalTo
    0.89
     Référence
    0.88
    expandindo
    0.88
    HasAnnotation
    0.87
     contextLoads
    0.85
    Activations Density 1.929%

    No Known Activations