© 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. 8787
    Prev
    Next
    INDEX
    Explanations

    various symbols, numbers, and formatting characters, especially in medical and technical contexts

    oai_token-act-pair · gemini-2.0-flash

    6

    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
     Però
    -0.61
     Idem
    -0.54
     Clarissa
    -0.50
     obscurity
    -0.50
    withstanding
    -0.50
     continuity
    -0.49
     OBO
    -0.48
     obstante
    -0.48
     rags
    -0.47
     Notion
    -0.47
    POSITIVE LOGITS
    protoimpl
    0.73
     protoimpl
    0.58
     незавершена
    0.57
    webElementXpaths
    0.56
    ThroughAttribute
    0.54
     Normdatei
    0.53
     resourceCulture
    0.53
    WebElementEntity
    0.50
    sidemargin
    0.49
     nahilalakip
    0.49
    Activations Density 3.096%

    No Known Activations