© 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. 3566
    Prev
    Next
    INDEX
    Explanations

    alternatives, lists, or choices, often indicated by the word "or."

    oai_token-act-pair · gemini-2.0-flash

    and or or

    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
    fromnode
    -0.85
    #+#
    -0.79
    /*
    -0.66
     MaterialApp
    -0.65
    :]:
    -0.65
    featureID
    -0.60
    SpringBootTest
    -0.60
    princ
    -0.60
     setuptools
    -0.59
    
    -0.59
    POSITIVE LOGITS
    <bos>
    0.65
     Aver
    0.45
    glBindBuffer
    0.45
     even
    0.43
    irei
    0.43
     ailleurs
    0.42
     forklar
    0.42
    ísima
    0.41
     Himo
    0.40
    carousel
    0.40
    Activations Density 1.960%

    No Known Activations