© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4683
    Prev
    Next
    INDEX
    Explanations

    text from scientific papers and analysis involving numbers, data, and experiments

    oai_token-act-pair · gemini-2.0-flash

    Scientific data analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     CGRect
    -0.60
     estekak
    -0.60
    +#+#
    -0.50
    DIPSETTING
    -0.49
     Indirect
    -0.48
    %");
    -0.48
    Hochspringen
    -0.47
     Modular
    -0.47
     LZ
    -0.47
     rollover
    -0.47
    POSITIVE LOGITS
     kasarigan
    0.71
    parsedMessage
    0.64
     weak
    0.59
    strong
    0.59
    peaks
    0.58
     strong
    0.57
    Strong
    0.57
     Strong
    0.55
    queryInterface
    0.54
    Weak
    0.53
    Activations Density 2.969%

    No Known Activations