© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13963
    Prev
    Next
    INDEX
    Explanations

    dots within the names of packages, classes, or files

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ujących
    -0.55
     colectiva
    -0.50
     suivantes
    -0.49
     suivants
    -0.46
    Опыт
    -0.46
    
    -0.45
    IANGLES
    -0.45
     Collège
    -0.44
     fué
    -0.44
    _>
    -0.43
    POSITIVE LOGITS
    ########.
    0.85
     defaultstate
    0.80
    Demografie
    0.71
    CodeAttribute
    0.65
    encodeWith
    0.65
    sizeCache
    0.65
     protoimpl
    0.64
     متعلقه
    0.61
    expandindo
    0.59
    orative
    0.59
    Activations Density 0.091%

    No Known Activations