© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15678
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ftagPool
    -0.70
     africains
    -0.69
     détru
    -0.69
     sauvages
    -0.66
     noires
    -0.65
    transQ
    -0.65
    StoryboardSegue
    -0.64
     gratuites
    -0.64
    setVerticalGroup
    -0.63
     BoxDecoration
    -0.63
    POSITIVE LOGITS
    生平
    0.52
    Hochspringen
    0.46
     ulti
    0.45
    Linki
    0.44
    лоси
    0.43
     j
    0.42
    Demografia
    0.42
    ΑΙ
    0.42
    #
    0.42
    жах
    0.41
    Activations Density 3.120%

    No Known Activations