© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10974
    Prev
    Next
    INDEX
    Explanations

    names of people, and family connections

    oai_token-act-pair · gemini-2.0-flash

    names and titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     iglesias
    -0.38
    /**
    -0.38
     civiles
    -0.36
     tedes
    -0.33
     scolas
    -0.32
    '
    -0.32
     ruinas
    -0.32
     escribió
    -0.32
    ：
    -0.31
     ejército
    -0.31
    POSITIVE LOGITS
    neſs
    0.90
    ſelves
    0.84
    djangoproject
    0.83
    ſelf
    0.82
     betweenstory
    0.79
    TestingModule
    0.74
    makeConstraints
    0.73
    ustimmung
    0.73
    ぼちゃ
    0.72
    UnusedPrivate
    0.72
    Activations Density 3.804%

    No Known Activations