© 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. 5019
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of mechanical processes

    oai_token-act-pair · gemini-2.0-flash

    propelled, thrown

    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
     interaction
    -1.09
     interactions
    -0.99
    interaction
    -0.95
     interact
    -0.93
     interacting
    -0.92
     Interactions
    -0.92
     Interaction
    -0.91
    Interaction
    -0.84
     interacts
    -0.82
     interacted
    -0.82
    POSITIVE LOGITS
    endphp
    0.62
     transported
    0.59
     pushed
    0.58
     thrown
    0.56
     propelled
    0.56
    MessageDigest
    0.54
     Zelanda
    0.53
     throws
    0.52
    bject
    0.52
    thrown
    0.50
    Activations Density 1.351%

    No Known Activations