© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11471
    Prev
    Next
    INDEX
    Explanations

    references to specific places, people, or organizations, often with a sense of location, association, or interaction.

    oai_token-act-pair · gemini-2.0-flash

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     surla
    -0.52
     defStyleAttr
    -0.48
     Exactos
    -0.46
     démarche
    -0.44
    ully
    -0.44
    最快更新
    -0.43
    perto
    -0.43
    новременно
    -0.43
     nakalista
    -0.43
    ours
    -0.41
    POSITIVE LOGITS
    клопе
    0.77
     iprot
    0.59
     EdgeInsets
    0.59
     MonoBehaviour
    0.59
    webElementXpaths
    0.57
    yargs
    0.55
    ComponentModel
    0.54
    sidemargin
    0.53
     estekak
    0.53
    ]")]
    0.52
    Activations Density 42.210%

    No Known Activations