Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13403
    Prev
    Next
    INDEX
    Explanations

    phrases like "by the way", "notice that", and words that express thought

    oai_token-act-pair · gemini-2.0-flash

    Giving instruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     متعلقه
    -0.62
     AssemblyProduct
    -0.62
    complexType
    -0.62
    KEYCODE
    -0.58
    tschaft
    -0.56
    InjectAttribute
    -0.54
    ]`
    -0.54
    rían
    -0.54
    Legături
    -0.53
    IInterface
    -0.53
    POSITIVE LOGITS
     note
    0.64
    Note
    0.61
    note
    0.60
     Note
    0.59
    aarrggbb
    0.55
     AssemblyCulture
    0.54
    banda
    0.54
    !*\
    0.50
    Crop
    0.49
     carri
    0.48
    Activations Density 1.668%

    No Known Activations