© 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. 6625
    Prev
    Next
    INDEX
    Explanations

    single characters on a newline

    oai_token-act-pair · gemini-2.0-flash

    legal/scientific document fragments

    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
    CloseOperation
    -0.70
    BeginInit
    -0.70
    .
    -0.64
    ceptable
    -0.59
    LayoutPanel
    -0.56
    jalá
    -0.55
    KommentareTeilen
    -0.54
     Bohn
    -0.54
    kamen
    -0.53
     ballast
    -0.52
    POSITIVE LOGITS
    tagHelperRunner
    0.82
    <bos>
    0.63
    JspWriter
    0.63
    $_['
    0.63
    ніципа
    0.60
     gärna
    0.59
     دیکھیے
    0.56
    odils
    0.56
    MigrationBuilder
    0.54
    Попис
    0.54
    Activations Density 2.011%

    No Known Activations