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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1738
    Prev
    Next
    INDEX
    Explanations

    words related to aging, decay, and luster

    oai_token-act-pair · gemini-2.0-flash

    shine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    memoized
    -0.53
    Imam
    -0.48
     verwijzen
    -0.47
    صحاب
    -0.47
    ็ง
    -0.46
     Imam
    -0.44
     crotch
    -0.44
    rvats
    -0.43
     psalm
    -0.42
     descrição
    -0.42
    POSITIVE LOGITS
     continúas
    0.72
     дописавши
    0.71
     صوتيه
    0.64
     GenerationType
    0.59
    LLocation
    0.57
    ')}}
    0.57
     متعلقه
    0.56
    contentLoaded
    0.54
    writeFieldEnd
    0.54
     endforeach
    0.53
    Activations Density 15.851%

    No Known Activations