© 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. 968
    Prev
    Next
    INDEX
    Explanations

    phrases containing "going on", "what is," and other similar references to current events.

    oai_token-act-pair · gemini-2.0-flash

    what's happening

    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
    ValueGeneration
    -0.54
    "}")
    -0.52
    fetchone
    -0.52
    ">)</
    -0.51
    /*
    -0.50
     وتسجيلات
    -0.49
    ագրություններ
    -0.48
    zzleHttp
    -0.48
    )");
    -0.48
    UnusedPrivate
    -0.47
    POSITIVE LOGITS
    tvguidetime
    0.63
     voici
    0.58
    Seni
    0.58
     సౌకర్య
    0.57
    Composable
    0.56
     scolaires
    0.56
     بيها
    0.55
     lèvres
    0.54
    ThroughAttribute
    0.54
    Managed
    0.53
    Activations Density 11.855%

    No Known Activations