© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3364
    Prev
    Next
    INDEX
    Explanations

    code snippets related to data serialization using protocol buffers

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
     dignité
    -1.00
     tartalomajánló
    -1.00
     enfans
    -1.00
     normaux
    -0.99
     scolaires
    -0.99
     démocr
    -0.98
     mères
    -0.98
    Datuak
    -0.97
     pères
    -0.95
     sauvages
    -0.94
    POSITIVE LOGITS
    <eos>
    0.31
    on
    0.29
    <bos>
    0.28
    an
    0.26
     
    0.26
    f
    0.23
    ↵↵
    0.22
    _
    0.22
    at
    0.21
    ma
    0.20
    Activations Density 4.931%

    No Known Activations