© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6183
    Prev
    Next
    INDEX
    Explanations

    words about wrapping, connecting, and tangling wires together

    oai_token-act-pair · gemini-2.0-flash

    wrapping around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Rhestr
    -0.58
    MLLoader
    -0.54
    otrop
    -0.50
    Attrib
    -0.46
    ebi
    -0.46
    vartis
    -0.46
    giau
    -0.45
    harma
    -0.45
     Crying
    -0.44
     飛
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.79
    enumi
    0.77
     esternos
    0.76
     propOrder
    0.73
    Datuak
    0.69
     дописавши
    0.68
    PerformLayout
    0.65
    GEBURTSDATUM
    0.65
    ScopeManager
    0.63
    ########.
    0.62
    Activations Density 0.674%

    No Known Activations