© 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. 8957
    Prev
    Next
    INDEX
    Explanations

    words that end with "ION", but also words like "DEFENDED", "CANDIDATES", "AFFILIATED", "RESPONS"

    oai_token-act-pair · gemini-2.0-flash

    Legal/technical texts

    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
    featureID
    -0.89
     AssemblyCulture
    -0.85
     MainAxisSize
    -0.81
     Efq
    -0.80
    PreferredItem
    -0.80
     ExecuteAsync
    -0.80
    styleType
    -0.80
     useAppContext
    -0.79
    #+#
    -0.78
     JpaRepository
    -0.77
    POSITIVE LOGITS
    ÉM
    0.47
    der
    0.45
    mes
    0.42
     Standard
    0.40
    ms
    0.40
    ve
    0.40
     White
    0.40
    CategoryName
    0.40
    ls
    0.39
    e
    0.39
    Activations Density 0.687%

    No Known Activations