© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3769
    Prev
    Next
    INDEX
    Explanations

    varied words, often adjectives and nouns with no clear unifying theme but with a possible leaning towards fantastical, humorous, childish and or literary context.

    oai_token-act-pair · gemini-2.0-flash

    artistic works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     design
    -1.30
     Design
    -1.03
    design
    -1.02
    Design
    -1.02
     performance
    -1.00
     creation
    -0.93
     diseño
    -0.90
     ontwerp
    -0.84
     DESIGN
    -0.84
    performance
    -0.83
    POSITIVE LOGITS
     ExecuteAsync
    0.71
    FirstResponder
    0.63
     NgModule
    0.62
    NOPQRST
    0.50
    {}
    0.50
    الإنجليزية
    0.50
    AnimationsModule
    0.48
    ונים
    0.48
    gefahr
    0.47
    phus
    0.47
    Activations Density 5.243%

    No Known Activations