© 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. 6837
    Prev
    Next
    INDEX
    Explanations

    a variety of words that don't seem to have a clear relation

    oai_token-act-pair · gemini-2.0-flash

    completion/change

    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
     autorytatywna
    -0.78
    ########.
    -0.71
    ArgsConstructor
    -0.67
    makeConstraints
    -0.66
     InputDecoration
    -0.65
    RegressionTest
    -0.65
    UnitTesting
    -0.65
    providedIn
    -0.65
    はじめに
    -0.64
    IntoConstraints
    -0.64
    POSITIVE LOGITS
     becomes
    1.02
     gets
    0.80
    becomes
    0.80
     become
    0.73
     succeeds
    0.70
     Becomes
    0.70
     turns
    0.68
     goes
    0.68
     completes
    0.68
     ends
    0.66
    Activations Density 4.574%

    No Known Activations