Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6838
    Prev
    Next
    INDEX
    Explanations

    biochemical processes and proteins, especially as they relate to inflammation and cell signaling

    oai_token-act-pair · gemini-2.0-flash

    experimental results

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     heiligen
    -0.64
    rungsseite
    -0.57
    quilo
    -0.54
    yns
    -0.52
    rairie
    -0.52
     Saltar
    -0.51
     prostu
    -0.50
     kohdetta
    -0.48
    rillation
    -0.48
     heilige
    -0.48
    POSITIVE LOGITS
     لينك
    0.59
     Pless
    0.54
    Šaltiniai
    0.54
     getopt
    0.53
    Embal
    0.52
    evap
    0.52
    FXMLLoader
    0.51
    ียด
    0.50
     SQLAlchemy
    0.49
     SafeMath
    0.49
    Activations Density 3.174%

    No Known Activations