© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1122
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to school operations at the end of the school year

    oai_token-act-pair · gemini-2.0-flash

    Distribution of resources

    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
    TypedDataSet
    -0.48
    itext
    -0.48
     Spisak
    -0.44
     <<<<<<<<<<<<<<
    -0.43
    ౌ
    -0.42
    لينكات
    -0.42
     Greeting
    -0.42
     Flyer
    -0.41
     presenti
    -0.41
    GEBURTSDATUM
    -0.41
    POSITIVE LOGITS
     defaultstate
    0.80
     CreateTagHelper
    0.64
    abestanden
    0.62
    dotenv
    0.62
    !*\
    0.61
     שוליים
    0.60
     f
    0.60
    GrantedAuthority
    0.60
    Przypisy
    0.59
    rativa
    0.59
    Activations Density 4.406%

    No Known Activations