© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2732
    Prev
    Next
    INDEX
    Explanations

    horizontal lines in formatted text and quotes, often in the context of code or technical documentation

    oai_token-act-pair · gemini-2.0-flash

    Figures and quoting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    hline
    -2.06
    cline
    -0.86
     كومونز
    -0.60
    /*
    -0.59
     الحره
    -0.57
     consist
    -0.49
    guém
    -0.48
    include
    -0.44
     eye
    -0.44
     doInBackground
    -0.43
    POSITIVE LOGITS
     Meksiku
    0.78
    OGND
    0.75
    DockStyle
    0.69
    IUrlHelper
    0.67
    AnchorStyles
    0.67
    GEBURTSDATUM
    0.65
    WithMany
    0.64
    elemField
    0.63
     feroit
    0.62
    Datuak
    0.62
    Activations Density 1.042%

    No Known Activations