© 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. 16195
    Prev
    Next
    INDEX
    Explanations

    content that refers to the Bharatiya Janata Party (BJP) or political elections, candidates, or leaders

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    脚注の使い方
    -0.74
    Демографія
    -0.71
    writeFieldEnd
    -0.69
    RenderAtEndOf
    -0.65
    Geplaatst
    -0.65
    endphp
    -0.63
    MessageTagHelper
    -0.62
    StructEnd
    -0.60
    cshtml
    -0.60
    __);
    -0.59
    POSITIVE LOGITS
    ɜ
    0.49
     golos
    0.48
    Hur
    0.48
     malheure
    0.47
    icia
    0.47
    ut
    0.47
     Klicken
    0.47
    ler
    0.45
     apsau
    0.45
    ONSORED
    0.45
    Activations Density 2.530%

    No Known Activations