© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11409
    Prev
    Next
    INDEX
    Explanations

    a variety of common words related to human interaction and activities.

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     оно
    -0.49
     มัน
    -0.48
     că
    -0.47
     которое
    -0.45
     diser
    -0.43
     nó
    -0.43
    čina
    -0.42
     它
    -0.42
    layoutManager
    -0.42
    mens
    -0.41
    POSITIVE LOGITS
    RenderAtEndOf
    0.96
    Personensuche
    0.85
     Roskov
    0.73
     strangers
    0.72
    __':
    0.72
    __*/
    0.72
    ंदीखरीदारी
    0.69
     /\.
    0.68
    GEBURTSDATUM
    0.68
     protoimpl
    0.66
    Activations Density 4.369%

    No Known Activations