© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10921
    Prev
    Next
    INDEX
    Explanations

    HTML code and CSS styling elements

    oai_token-act-pair · gemini-2.0-flash

    HTML elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    DispatchToProps
    -0.60
    __":
    -0.56
    ReusableCell
    -0.54
    CppMethod
    -0.54
    standers
    -0.53
    "}"
    -0.53
    insegna
    -0.51
     veuillez
    -0.50
    ToProps
    -0.50
    "¿
    -0.50
    POSITIVE LOGITS
    twimg
    0.79
     Baillargeon
    0.76
    rmtree
    0.69
    PMailer
    0.67
    rshire
    0.66
    TagMode
    0.66
     BorderRadius
    0.65
     Roskov
    0.64
    뀜
    0.63
    Personendaten
    0.63
    Activations Density 0.984%

    No Known Activations