© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3620
    Prev
    Next
    INDEX
    Explanations

    words related to software updates, lists, and technical documentation

    oai_token-act-pair · gemini-2.0-flash

    changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     artesanales
    -0.52
     vectorielle
    -0.48
     artificiales
    -0.46
     nucléaire
    -0.45
     pensamientos
    -0.45
    aspectj
    -0.43
     gedachten
    -0.42
     financieras
    -0.41
    евна
    -0.39
     judiciales
    -0.39
    POSITIVE LOGITS
    featureID
    0.75
    LookAnd
    0.65
    StoryboardSegue
    0.62
    queryInterface
    0.61
     Cataloging
    0.57
     feature
    0.56
    зулта
    0.56
    VersionUID
    0.55
    клопе
    0.53
    hern
    0.52
    Activations Density 2.824%

    No Known Activations