© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 10001
    Prev
    Next
    INDEX
    Explanations

    words describing progress, or successful completion

    oai_token-act-pair · gemini-2.0-flash

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.71
    Datuak
    -0.71
    InjectAttribute
    -0.67
    contentLoaded
    -0.66
    IsMutable
    -0.66
     Савезне
    -0.65
    RegistryLite
    -0.64
     otomatig
    -0.64
    клопе
    -0.63
     دیکھیے
    -0.62
    POSITIVE LOGITS
    respectively
    0.52
    הערות
    0.52
    Referències
    0.47
     Primero
    0.47
     Supremo
    0.44
     tén
    0.43
     Ceux
    0.43
    OnInit
    0.43
    Activités
    0.42
     avantaj
    0.42
    Activations Density 8.824%

    No Known Activations