Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13900
    Prev
    Next
    INDEX
    Explanations

    words related to conditions, environments, or status related to a noun.

    oai_token-act-pair · gemini-2.0-flash

    level

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    elemField
    -0.74
     AssemblyTitle
    -0.71
    الإنجليزية
    -0.68
    ########.
    -0.65
     jLabel
    -0.65
    URLException
    -0.63
     actionTypes
    -0.63
     Réponses
    -0.61
    __':
    -0.60
     jScrollPane
    -0.60
    POSITIVE LOGITS
     level
    0.88
     levels
    0.81
     niveau
    0.78
     niveaux
    0.73
    level
    0.73
    水平
    0.67
     livelli
    0.65
     úrov
    0.65
    levels
    0.64
    Level
    0.63
    Activations Density 2.533%

    No Known Activations