© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10396
    Prev
    Next
    INDEX
    Explanations

    text that describes Amazon Kinesis Data Streams

    oai_token-act-pair · gemini-2.0-flash

    manage

    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
     itſelf
    -0.98
     purpoſe
    -0.97
     myſelf
    -0.95
     pleaſure
    -0.94
     Diſ
    -0.93
     ſever
    -0.91
    PMailer
    -0.90
     raiſ
    -0.90
    SBATCH
    -0.90
     himſelf
    -0.89
    POSITIVE LOGITS
     man
    0.62
     manage
    0.52
     Man
    0.51
     auto
    0.50
     MAN
    0.49
    man
    0.48
     fine
    0.46
     Auto
    0.44
    manage
    0.42
     Manage
    0.41
    Activations Density 2.085%

    No Known Activations