© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5570
    Prev
    Next
    INDEX
    Explanations

    words that are grammatical conjunctions, auxiliary verbs, or prepositions.

    oai_token-act-pair · gemini-2.0-flash

    academic writing

    np_max-act-logits · 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
    ise
    -0.45
    Adapt
    -0.44
    isation
    -0.42
    тин
    -0.40
    newcommand
    -0.39
    ises
    -0.39
     tangle
    -0.38
    ised
    -0.37
     تجمع
    -0.37
     simplification
    -0.37
    POSITIVE LOGITS
     normal
    1.02
    normal
    0.86
     regular
    0.84
    personal
    0.82
    AndEndTag
    0.79
     personal
    0.79
     formal
    0.79
    regular
    0.77
    formal
    0.75
     institutional
    0.75
    Activations Density 5.450%

    No Known Activations