© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6186
    Prev
    Next
    INDEX
    Explanations

    Chinese file description information

    oai_token-act-pair · gemini-2.0-flash

    programming/web content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     auffi
    -0.96
     itſelf
    -0.79
     dieß
    -0.75
     ſta
    -0.75
     iſt
    -0.74
     purpoſe
    -0.74
     chrétien
    -0.73
     raiſ
    -0.71
     ſche
    -0.71
     ſol
    -0.69
    POSITIVE LOGITS
     a
    0.47
    WebRequest
    0.39
     <",
    0.38
     the
    0.38
    ContentAsync
    0.34
    ات
    0.34
     ,
    0.34
    ,
    0.34
    ™,
    0.33
    󠁢
    0.33
    Activations Density 1.597%

    No Known Activations