© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12536
    Prev
    Next
    INDEX
    Explanations

    python code blocks including the word 'command' and acronyms like 'acr'

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    seigneur
    -0.50
    CLUSIVE
    -0.49
    strcmp
    -0.47
    gings
    -0.47
    Unfinished
    -0.46
     Carn
    -0.45
    onec
    -0.44
     belts
    -0.44
     trou
    -0.44
     pulseira
    -0.43
    POSITIVE LOGITS
    <bos>
    0.83
     disambiguazione
    0.77
    (!__
    0.75
     للمعارف
    0.73
    SourceChecksum
    0.71
    hyrchwyd
    0.70
    XmlAccessType
    0.70
    SequentialGroup
    0.65
    ніципалі
    0.65
     Jerusalén
    0.64
    Activations Density 12.641%

    No Known Activations