© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3075
    Prev
    Next
    INDEX
    Explanations

    gene names or other genetic codes

    oai_token-act-pair · gemini-2.0-flash

    Greek letters and numerals

    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
    <bos>
    -0.77
    bro
    -0.43
    рти
    -0.41
     ciento
    -0.40
    CrossRef
    -0.37
    Archive
    -0.36
    दि
    -0.36
     Lond
    -0.36
    Ђ
    -0.35
    akter
    -0.34
    POSITIVE LOGITS
    astéroïdes
    0.91
    MessageOf
    0.84
     Normdatei
    0.83
     pinulongan
    0.80
     AssemblyCulture
    0.79
    Tikang
    0.79
     виправивши
    0.78
     للمعارف
    0.78
     TextInputType
    0.77
     '\\;'
    0.76
    Activations Density 2.138%

    No Known Activations