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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14817
    Prev
    Next
    INDEX
    Explanations

    a broad range of words associated with dating profiles, relationships, science results or community consequences.

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    ConstraintMaker
    -0.82
     ExecuteAsync
    -0.82
     كومونز
    -0.78
    DockStyle
    -0.76
     ostavi
    -0.76
    PerformLayout
    -0.73
     protoimpl
    -0.72
    Aiheesta
    -0.71
    principalColumn
    -0.70
     cdti
    -0.69
    POSITIVE LOGITS
     and
    1.77
     &
    1.20
     \&
    1.01
     or
    0.85
    และ
    0.81
    and
    0.77
    和
    0.75
    および
    0.74
     и
    0.73
    /
    0.70
    Activations Density 4.855%

    No Known Activations