Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1174
    Prev
    Next
    INDEX
    Explanations

    verbs and verb fragments related to human interaction and activities

    oai_token-act-pair · gemini-2.0-flash

    connection/joining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    CppCodeGen
    -0.63
    SuppressLint
    -0.63
    datatables
    -0.57
    Dtos
    -0.52
     Receive
    -0.52
    qrstuvwxyz
    -0.51
     a
    -0.50
     receive
    -0.49
    νώ
    -0.49
     ivelany
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.65
    AccessorTable
    0.60
    IUrlHelper
    0.57
    DotNetBar
    0.56
    tagHelperRunner
    0.56
     étoit
    0.55
     psicológico
    0.54
     becauſe
    0.54
    AutoScaleMode
    0.53
     Swedes
    0.51
    Activations Density 2.315%

    No Known Activations