© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4084
    Prev
    Next
    INDEX
    Explanations

    "I" as a subject, and auxiliary verbs can, could, to be and to do related to the subject

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    PreferredItem
    -0.96
    ArrowToggle
    -0.88
     >=",
    -0.88
    __':
    -0.88
    +#+#
    -0.86
    InitVars
    -0.86
    MLLoader
    -0.85
    ']))
    -0.85
     cherchés
    -0.81
     kasarigan
    -0.81
    POSITIVE LOGITS
     content
    0.44
    book
    0.40
     time
    0.39
    orial
    0.38
     Del
    0.37
     stage
    0.36
     source
    0.35
    ந
    0.35
     бру
    0.35
    ENOT
    0.34
    Activations Density 1.682%

    No Known Activations