© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10014
    Prev
    Next
    INDEX
    Explanations

    phrases about potential and the pronouns 'he' and 'his'

    oai_token-act-pair · gemini-2.0-flash

    potential

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyVersion
    -0.68
     AssemblyCulture
    -0.63
    Демографія
    -0.59
    MessageTagHelper
    -0.59
    はじめに
    -0.58
    UrlResolution
    -0.56
     चीज़ों
    -0.51
     кӀ
    -0.50
     viewType
    -0.49
    weile
    -0.47
    POSITIVE LOGITS
     potential
    2.83
    potential
    2.63
     Potential
    2.59
    Potential
    2.58
     POTENTIAL
    2.30
     potencial
    2.08
     potentials
    2.08
     potentiel
    2.02
     potensi
    1.80
     potenciales
    1.78
    Activations Density 1.803%

    No Known Activations