© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15888
    Prev
    Next
    INDEX
    Explanations

    references to a specific person, Ilobe, and related context

    oai_token-act-pair · gemini-2.0-flash

    Nigerian names/places and code

    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
    rungsseite
    -0.66
    بوابة
    -0.62
    HttpFoundation
    -0.59
    esgue
    -0.56
    SBATCH
    -0.54
     AssemblyProduct
    -0.52
    InputBorder
    -0.52
    NameInMap
    -0.52
     splet
    -0.52
    ाहरण
    -0.52
    POSITIVE LOGITS
    "}")
    0.48
    currentItem
    0.47
     Declare
    0.47
    leste
    0.46
     }},
    0.45
    moveToFirst
    0.45
    étranger
    0.44
    )))),
    0.44
    "}},
    0.43
    efore
    0.42
    Activations Density 4.672%

    No Known Activations