© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7290
    Prev
    Next
    INDEX
    Explanations

    words related to scientific measurements or the association of entities

    oai_token-act-pair · gemini-2.0-flash

    subject, target

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    plating
    -0.50
    ImageContext
    -0.49
    koľvek
    -0.49
    ControllerAdvice
    -0.48
     nôtre
    -0.47
     تانيه
    -0.47
    RegistryLite
    -0.46
     PARSER
    -0.46
     بتاريخ
    -0.43
    FilterChain
    -0.42
    POSITIVE LOGITS
     subject
    1.04
    subject
    0.93
     Subject
    0.92
    Subject
    0.86
     target
    0.85
     subjects
    0.76
     targets
    0.75
     Subjects
    0.73
     Target
    0.73
    target
    0.73
    Activations Density 1.646%

    No Known Activations