© 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. 11270
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to data analysis of groups and/or their distribution over time/space.

    oai_token-act-pair · gemini-2.0-flash

    specific scientific terminology or jargon

    np_token-act-pair-logits · gpt-4o-mini

    locations

    np_max-act-logits · gemini-2.0-flash
    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
     across
    -1.50
     Across
    -1.42
    across
    -1.39
    Across
    -1.36
     ACROSS
    -1.23
     various
    -0.85
    various
    -0.85
     varying
    -0.75
     varied
    -0.75
     varies
    -0.72
    POSITIVE LOGITS
     kasarigan
    0.81
    LLocation
    0.69
     Paglinawan
    0.67
    abetes
    0.67
    Források
    0.61
    Jeografia
    0.58
    oredCriteria
    0.57
    SharedDtor
    0.55
    ItemBackground
    0.55
    kuuta
    0.54
    Activations Density 3.165%

    No Known Activations