© 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. 8468
    Prev
    Next
    INDEX
    Explanations

    legal terminology and code snippets

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     mourners
    -0.52
     getItemId
    -0.52
     BoxFit
    -0.52
     service
    -0.50
     orphanage
    -0.49
    зулта
    -0.49
     itſelf
    -0.48
     parishioners
    -0.48
     deceased
    -0.47
     mädchen
    -0.47
    POSITIVE LOGITS
    principalColumn
    0.64
    UserScript
    0.64
    mybatisplus
    0.60
     jadx
    0.59
    nonatomic
    0.59
    CodeDom
    0.57
    LookAnd
    0.56
    :^(
    0.55
    TagMode
    0.55
     erk
    0.54
    Activations Density 10.499%

    No Known Activations