© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3181
    Prev
    Next
    INDEX
    Explanations

    names of people

    oai_token-act-pair · gemini-2.0-flash

    saying/reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    存于互联网档案馆
    -0.74
    verwijspagina
    -0.70
     Himo
    -0.69
    DockStyle
    -0.69
    VersionUID
    -0.66
    Rptr
    -0.65
    SharedDtor
    -0.63
    脚注の使い方
    -0.62
     تضيفلها
    -0.62
    原始内容存档于
    -0.62
    POSITIVE LOGITS
     predicted
    0.55
     said
    0.53
    "]];
    0.52
     warned
    0.51
    Бахар
    0.50
    "}"
    0.50
     lät
    0.47
     εί
    0.47
     told
    0.46
     conceded
    0.46
    Activations Density 3.894%

    No Known Activations