© 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. 14689
    Prev
    Next
    INDEX
    Explanations

    exceptions or conditions

    oai_token-act-pair · gemini-2.0-flash

    unless

    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
    +#+#
    -0.91
     مشين
    -0.80
    IntoConstraints
    -0.69
    #+#
    -0.68
    Tembelea
    -0.66
    abestanden
    -0.66
    ;">
    -0.65
     myſelf
    -0.64
    Xna
    -0.64
    fromnode
    -0.64
    POSITIVE LOGITS
    <bos>
    0.75
    require
    0.50
     giud
    0.49
    rów
    0.48
    百科
    0.48
    U
    0.45
    r
    0.44
     back
    0.43
    -
    0.43
    '
    0.42
    Activations Density 2.140%

    No Known Activations