© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1476
    Prev
    Next
    INDEX
    Explanations

    positive and descriptive adjectives

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     SwiftUI
    -0.72
    GraphicsUnit
    -0.67
     referrerpolicy
    -0.65
     forState
    -0.64
    webElement
    -0.64
    pperware
    -0.63
     }}">
    -0.62
    BufferException
    -0.62
    addKeyListener
    -0.60
    complexType
    -0.59
    POSITIVE LOGITS
     متعلقه
    0.72
     Joaquín
    0.49
     againſt
    0.47
     Majefty
    0.47
    oule
    0.43
     ſet
    0.43
    Edge
    0.43
    rande
    0.42
     fhew
    0.42
     laſt
    0.42
    Activations Density 9.131%

    No Known Activations