© 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. 9183
    Prev
    Next
    INDEX
    Explanations

    phrases containing "life", "world", "day", "car", "craft", or "practice" prefaced by a hyphen or other word

    oai_token-act-pair · gemini-2.0-flash

    real-world events

    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
    <bos>
    -0.71
     neve
    -0.61
     BufferedReader
    -0.60
     tslint
    -0.48
     lief
    -0.46
    EnableWeb
    -0.46
    ribune
    -0.45
     Benefit
    -0.45
     contextLoads
    -0.45
    子を
    -0.44
    POSITIVE LOGITS
    ếng
    0.71
     springfox
    0.59
    ReusableCell
    0.57
     Templ
    0.57
    ruma
    0.56
     intermédiaire
    0.53
    ownership
    0.52
     chimiques
    0.52
     templ
    0.51
     esperienze
    0.51
    Activations Density 0.907%

    No Known Activations