© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9577
    Prev
    Next
    INDEX
    Explanations

    the word 'level', particularly in the context of scientific data and measurements

    oai_token-act-pair · gemini-2.0-flash

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     level
    -2.92
    Level
    -2.67
     Level
    -2.66
    level
    -2.63
     LEVEL
    -2.48
     levels
    -2.30
    LEVEL
    -2.28
    levels
    -2.13
     Levels
    -2.11
     nivel
    -2.00
    POSITIVE LOGITS
     Folio
    0.64
     Rota
    0.59
     Mandi
    0.58
    utnik
    0.58
    ArgsConstructor
    0.57
    GeoNames
    0.57
     Assignee
    0.54
     Lehre
    0.54
    riente
    0.53
    IMPORTED
    0.52
    Activations Density 0.278%

    No Known Activations