© 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. 6502
    Prev
    Next
    INDEX
    Explanations

    numbers and math symbols in tables, likely flagging statistical results

    oai_token-act-pair · gemini-2.0-flash

    8 and 9

    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
    StoreMessageInfo
    -0.62
     EconPapers
    -0.57
    IsContent
    -0.57
     resourceCulture
    -0.55
    __*/
    -0.53
    تقاوى
    -0.53
    complexContent
    -0.52
     ostavi
    -0.52
    ंदीखरीदारी
    -0.51
     للمعارف
    -0.50
    POSITIVE LOGITS
    8
    1.88
    9
    1.59
     eighth
    1.53
     eight
    1.44
     Eighth
    1.41
     Eight
    1.33
     nine
    1.31
     ninth
    1.31
    7
    1.24
    ８
    1.21
    Activations Density 8.400%

    No Known Activations