© 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. 810
    Prev
    Next
    INDEX
    Explanations

    code related to setting and getting Protobuf messages and their properties, especially optional ones

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    :✨
    -0.59
    はじめに
    -0.55
     initComponents
    -0.54
     собі
    -0.52
    adhy
    -0.52
    nthetic
    -0.51
    emark
    -0.51
     Warburton
    -0.51
    Harm
    -0.50
    addContainerGap
    -0.50
    POSITIVE LOGITS
     ContentValues
    0.58
    amaño
    0.47
    Geschiedenis
    0.46
    Sziasztok
    0.45
     oliveira
    0.45
    atmosfera
    0.45
    ñora
    0.44
    SharedCtor
    0.44
    ?),
    0.44
     useAuth
    0.44
    Activations Density 4.973%

    No Known Activations