© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1318
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to formal reports, research, and official communication

    oai_token-act-pair · gemini-2.0-flash

    how things work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     betweenstory
    -1.06
    BufferException
    -0.91
     Roskov
    -0.90
    Personendaten
    -0.90
    TagMode
    -0.90
     Мексичка
    -0.87
    MLLoader
    -0.86
     AssemblyProduct
    -0.86
     calendriers
    -0.84
    Portale
    -0.82
    POSITIVE LOGITS
     vanlig
    0.45
    쓸
    0.45
     kebenaran
    0.44
     typically
    0.41
     otthon
    0.41
    やる
    0.41
     altid
    0.40
     químicas
    0.40
    </h1>
    0.40
     commonly
    0.40
    Activations Density 3.714%

    No Known Activations