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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7049
    Prev
    Next
    INDEX
    Explanations

    place names and "New York Times"

    oai_token-act-pair · gemini-2.0-flash

    New York Times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     AttributeSet
    -0.78
    IntoConstraints
    -0.65
    Rohy
    -0.65
    TypedDataSet
    -0.64
    pulumi
    -0.63
    CodedInputStream
    -0.62
     Chwiliwch
    -0.61
     noten
    -0.60
    кобрита
    -0.60
    ريقة
    -0.60
    POSITIVE LOGITS
     Pire
    0.59
    ത്ര
    0.53
    uracy
    0.53
    SourceChecksum
    0.53
    depend
    0.52
    Depend
    0.52
     UINT
    0.51
    3
    0.50
     toàn
    0.50
    pmatrix
    0.50
    Activations Density 0.227%

    No Known Activations