© 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. 8449
    Prev
    Next
    INDEX
    Explanations

    words in URLs, especially hyphenated words within a URL

    oai_token-act-pair · gemini-2.0-flash

    say "-"

    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
     Universitaria
    -0.89
     Monfieur
    -0.88
     Shaksp
    -0.88
     Económica
    -0.87
     Efq
    -0.85
     Escolar
    -0.84
     Cæsar
    -0.83
     
    -0.82
    ientôt
    -0.82
    latego
    -0.81
    POSITIVE LOGITS
    -
    0.66
      
    0.59
    /
    0.54
    ial
    0.44
    -/
    0.44
    </strong>
    0.43
    ​
    0.39
    ini
    0.39
    chen
    0.39
    ka
    0.39
    Activations Density 7.620%

    No Known Activations