© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16323
    Prev
    Next
    INDEX
    Explanations

    keywords indicating the start of a definition in code, such as 'public', 'static', 'const', and 'using'

    oai_token-act-pair · gemini-2.0-flash

    Code access modifiers

    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
     Monfieur
    -1.05
     Efq
    -1.00
     becauſe
    -0.97
     myſelf
    -0.96
     оригіналу
    -0.93
     reaſon
    -0.93
     leaſt
    -0.90
     whoſe
    -0.88
     themſelves
    -0.87
     ſeveral
    -0.87
    POSITIVE LOGITS
    <bos>
    0.54
    -
    0.43
    ;
    0.43
    *
    0.42
    (
    0.41
    :
    0.40
    /
    0.39
    �
    0.39
    ''
    0.38
    ★
    0.38
    Activations Density 1.332%

    No Known Activations