© 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. 4338
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a claim is being proven or justified

    oai_token-act-pair · gemini-2.0-flash

    demonstrating, proving

    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
    djangoproject
    -0.60
     كومونز
    -0.59
    Bronnen
    -0.47
    userdetails
    -0.46
    rip
    -0.44
    Източници
    -0.43
    itename
    -0.43
    yarnpkg
    -0.43
    ViewFeatures
    -0.42
    rici
    -0.42
    POSITIVE LOGITS
     demonstrating
    1.69
     demonstrate
    1.68
     demonstrates
    1.67
     proves
    1.61
     proof
    1.60
     prove
    1.55
     demostrar
    1.54
     proving
    1.51
     demonstrated
    1.49
    证明
    1.48
    Activations Density 2.183%

    No Known Activations