© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13033
    Prev
    Next
    INDEX
    Explanations

    hexadecimal and other numerical codes with specific formatting

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     destination
    -0.51
    ágot
    -0.50
    plona
    -0.50
    AAT
    -0.50
     بوت
    -0.49
    cillor
    -0.48
     Kapp
    -0.47
    aspetto
    -0.47
     contextLoads
    -0.47
    oning
    -0.47
    POSITIVE LOGITS
    UnusedPrivate
    0.73
     مُعرِّف
    0.71
     unknownFields
    0.70
    تقاوى
    0.70
     CreateTagHelper
    0.69
    zzleHttp
    0.68
    хьтан
    0.68
    FXMLLoader
    0.66
     ModelExpression
    0.65
     Référence
    0.65
    Activations Density 1.403%

    No Known Activations