© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    content containing research or investigations

    oai_token-act-pair · gemini-2.0-flash

    Information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     administration
    -1.27
     Administration
    -1.09
    administration
    -1.02
    Administration
    -0.98
     ADMINISTRATION
    -0.93
     administrations
    -0.93
    IntoConstraints
    -0.88
     admin
    -0.84
    ministrazione
    -0.78
    admin
    -0.75
    POSITIVE LOGITS
     on
    0.73
     AssemblyProduct
    0.62
    וויק
    0.55
     about
    0.54
     relativa
    0.51
     sobre
    0.51
     SOBRE
    0.49
     relative
    0.46
     gratuite
    0.46
    כון
    0.46
    Activations Density 1.145%

    No Known Activations