© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15503
    Prev
    Next
    INDEX
    Explanations

    technical and scientific writing related to materials

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    rungsseite
    -0.48
     fallait
    -0.45
     picked
    -0.44
     pick
    -0.43
     pickups
    -0.40
     Alph
    -0.39
     picks
    -0.39
    pick
    -0.38
    tij
    -0.38
    omiast
    -0.38
    POSITIVE LOGITS
    awtextra
    0.77
    Bronnen
    0.71
    tagHelperRunner
    0.71
    __":
    0.69
    AnchorStyles
    0.69
    ".
    0.69
    Personensuche
    0.68
    RequiresApi
    0.66
    SerializedSize
    0.65
    CPtr
    0.65
    Activations Density 3.300%

    No Known Activations