© 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. 8897
    Prev
    Next
    INDEX
    Explanations

    proper nouns (names of people and places) and words associated with political entities or actions.

    oai_token-act-pair · gemini-2.0-flash

    names

    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
     EconPapers
    -0.78
    IndentedString
    -0.77
     externi
    -0.76
    SharedDtor
    -0.72
    yntaxException
    -0.68
    Демографія
    -0.67
     MenuView
    -0.66
     jspb
    -0.66
    WithIOException
    -0.66
     createSprite
    -0.65
    POSITIVE LOGITS
    +:+
    0.54
     Syed
    0.52
     Khaled
    0.46
     col
    0.46
     Merdeka
    0.44
     Saleh
    0.44
     Mohammad
    0.43
     Jamal
    0.43
     Ahmad
    0.43
     Aziz
    0.43
    Activations Density 12.536%

    No Known Activations