© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 16039
    Prev
    Next
    INDEX
    Explanations

    emotionally charged negative statements expressing disagreement

    oai_token-act-pair · gemini-2.0-flash

    Nonsense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    glVertex
    -0.64
    gatsby
    -0.59
     /\.
    -0.58
    ricians
    -0.56
    écution
    -0.54
     /\.(
    -0.51
     henvisninger
    -0.51
    oucí
    -0.49
    ねる
    -0.49
    发表于
    -0.48
    POSITIVE LOGITS
     noise
    0.77
     garbage
    0.76
     rubbish
    0.71
     junk
    0.70
     crap
    0.70
     trash
    0.69
     nonsense
    0.67
     fodder
    0.65
    noise
    0.64
     sludge
    0.63
    Activations Density 2.078%

    No Known Activations