© 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. 116
    Prev
    Next
    INDEX
    Explanations

    a diverse cluster of different and sometimes seemingly unrelated topics, including planets, space, job listings, negative sentiment, and injury

    oai_token-act-pair · gemini-2.0-flash

    science fiction/fantasy

    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
     autorytatywna
    -0.71
    AccessorTable
    -0.68
    المشاركات
    -0.61
     дописавши
    -0.61
    ']));
    -0.59
    protoimpl
    -0.58
    UIControlState
    -0.57
    ýt
    -0.56
    oa̍t
    -0.56
    findpost
    -0.52
    POSITIVE LOGITS
     '\\;'
    0.52
    EndContext
    0.51
    withIdentifier
    0.49
    tvb
    0.46
     Pelt
    0.43
    SuppressMessage
    0.42
     Praxis
    0.42
     Jef
    0.42
    بینی
    0.41
     pach
    0.41
    Activations Density 2.057%

    No Known Activations