© 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. 8745
    Prev
    Next
    INDEX
    Explanations

    general common words such as "is" or "for" in technical or mathematical contexts

    oai_token-act-pair · gemini-2.0-flash

    clearly

    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
    utnik
    -0.53
     lắm
    -0.51
    Probably
    -0.51
     '*':
    -0.49
    :✨
    -0.48
    arsk
    -0.47
    LookUp
    -0.47
     Probably
    -0.47
     EconPapers
    -0.47
    HasAnnotation
    -0.46
    POSITIVE LOGITS
     clearly
    3.00
    clearly
    2.75
     Clearly
    2.41
    Clearly
    2.25
     claramente
    1.92
     clairement
    1.91
     chiaramente
    1.73
     plainly
    1.72
     jelas
    1.34
     rõ
    1.30
    Activations Density 16.004%

    No Known Activations