© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6636
    Prev
    Next
    INDEX
    Explanations

    the string "tr"

    oai_token-act-pair · gemini-2.0-flash

    tr

    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
    ↵↵
    -0.78
     par
    -0.70
     Par
    -0.66
    ↵
    -0.65
     sem
    -0.64
    <eos>
    -0.64
    Par
    -0.60
    .
    -0.60
     Mal
    -0.60
    ia
    -0.59
    POSITIVE LOGITS
     Efq
    1.38
     myſelf
    1.32
     ſeveral
    1.29
     Theſe
    1.28
     Monfieur
    1.24
     whoſe
    1.23
     auroit
    1.20
     becauſe
    1.20
     purpoſe
    1.16
     Jefus
    1.15
    Activations Density 2.288%

    No Known Activations