© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2976
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to working and relationships.

    oai_token-act-pair · gemini-2.0-flash

    effort and work

    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
    ########.
    -0.63
    RSpec
    -0.47
    AddRange
    -0.43
     [*]
    -0.43
     পর
    -0.42
    igable
    -0.41
    toContain
    -0.40
    sterna
    -0.40
    atihan
    -0.40
    ster
    -0.40
    POSITIVE LOGITS
     المعيارى
    0.75
     above
    0.73
    yntaxException
    0.69
     للاسماء
    0.69
    above
    0.66
    Above
    0.64
     géographie
    0.61
     im
    0.61
     protoimpl
    0.59
    المكان
    0.59
    Activations Density 4.775%

    No Known Activations