© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13175
    Prev
    Next
    INDEX
    Explanations

    phrases involving seeing, understanding, and exploitation

    oai_token-act-pair · gemini-2.0-flash

    awareness, perception, understanding

    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
    NameInMap
    -0.82
    marshaller
    -0.79
    StoryboardSegue
    -0.77
    DeleteBehavior
    -0.77
    Rüyada
    -0.75
    ThroughAttribute
    -0.75
    djangoproject
    -0.74
    CppMethod
    -0.72
     &___
    -0.71
    InputTagHelper
    -0.69
    POSITIVE LOGITS
     "','
    0.41
     знаешь
    0.40
    就知道
    0.39
    माण
    0.39
     privados
    0.39
    imax
    0.39
    createStatement
    0.39
     clearly
    0.37
    [$
    0.36
    abá
    0.36
    Activations Density 2.070%

    No Known Activations