© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3925
    Prev
    Next
    INDEX
    Explanations

    groups of adjectives and nouns that follow the word "a"

    oai_token-act-pair · gemini-2.0-flash

    Romantic/erotic/violent stories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     مرئيه
    -0.77
    AddTagHelper
    -0.71
    исленность
    -0.64
    ViewFeatures
    -0.63
     GenerationType
    -0.62
    Personendaten
    -0.62
     JpaRepository
    -0.61
    DebuggerNonUser
    -0.60
    Références
    -0.60
     &___
    -0.60
    POSITIVE LOGITS
     OMITBAD
    0.57
     who
    0.52
     للمعارف
    0.47
    (&(
    0.45
    demia
    0.45
    diğimiz
    0.44
    who
    0.44
     ostavi
    0.44
     dynamic
    0.44
     Po
    0.43
    Activations Density 1.826%

    No Known Activations