© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14681
    Prev
    Next
    INDEX
    Explanations

    javascript code comments related to locating views, objects, and elements

    oai_token-act-pair · gemini-2.0-flash

    code elements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    estacks
    -0.55
     متعلقه
    -0.52
    SceneManagement
    -0.50
     betweenstory
    -0.47
     Highlanders
    -0.46
     trinh
    -0.45
     algas
    -0.44
     Fiske
    -0.44
     Irak
    -0.43
    Personensuche
    -0.42
    POSITIVE LOGITS
    SizeF
    0.59
     QWidget
    0.57
     aceptas
    0.56
     hashCode
    0.56
     față
    0.55
     GetEnumerator
    0.54
     ujednoznacz
    0.54
    译
    0.52
    seded
    0.52
    Dě
    0.51
    Activations Density 26.857%

    No Known Activations