© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11176
    Prev
    Next
    INDEX
    Explanations

    reserved words and identifiers in code samples

    oai_token-act-pair · gemini-2.0-flash

    programming keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     <<<<<<<<<<<<<<
    -0.71
    EndContext
    -0.68
    ])):
    -0.59
    "]:
    -0.57
    RequiresApi
    -0.56
    ]):
    -0.56
    ?}",
    -0.56
    AndEndTag
    -0.55
    原始内容存档于
    -0.55
    istoitu
    -0.55
    POSITIVE LOGITS
     Monfieur
    0.86
     myſelf
    0.78
     itſelf
    0.76
     uſed
    0.75
     paſſ
    0.75
     pleaſure
    0.75
     raiſ
    0.73
     ſee
    0.73
    <bos>
    0.72
     reaſon
    0.72
    Activations Density 1.112%

    No Known Activations