© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9578
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing actions and quality with a potential bias toward sexual content.

    oai_token-act-pair · gemini-2.0-flash

    actions being done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     beginnetje
    -1.03
    <bos>
    -0.85
     emerge
    -0.81
     emerging
    -0.79
     émer
    -0.78
    GOTREF
    -0.76
    sizeCache
    -0.75
     emerged
    -0.73
     emerges
    -0.72
    Emerging
    -0.72
    POSITIVE LOGITS
     multilateral
    0.58
    jango
    0.54
    RunAsync
    0.52
     dope
    0.52
     Conductor
    0.51
    dox
    0.50
    kuuta
    0.49
    humid
    0.49
    elementType
    0.48
     kulit
    0.47
    Activations Density 1.360%

    No Known Activations