© 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. 9079
    Prev
    Next
    INDEX
    Explanations

    code-related tokens and formatting, possibly in languages like Swift or related to network requests.

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
     étoit
    -0.57
     avoient
    -0.49
     feroit
    -0.48
     pouvoit
    -0.48
     aikaa
    -0.48
     auroit
    -0.47
     étoient
    -0.47
     fotografico
    -0.47
     florales
    -0.45
    bebasan
    -0.44
    POSITIVE LOGITS
     يتيمه
    1.01
    RegressionTest
    0.80
    OGND
    0.79
    AccessorTable
    0.79
     betweenstory
    0.76
     noDo
    0.76
    
    0.74
    TypedDataSet
    0.73
    sizeCache
    0.73
     насељу
    0.73
    Activations Density 3.156%

    No Known Activations