© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5530
    Prev
    Next
    INDEX
    Explanations

    a variety of uncommon short sequences of letters in different contexts, but seems to activate most strongly on "pal"

    oai_token-act-pair · gemini-2.0-flash

    Scientific and technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    __":
    -0.74
    expandindo
    -0.71
    writeFieldEnd
    -0.67
    Autoritní
    -0.66
     onCreateView
    -0.66
    Française
    -0.66
    urfs
    -0.65
    (;;)
    -0.65
    RTLE
    -0.65
    KURZBESCHREIBUNG
    -0.64
    POSITIVE LOGITS
    <bos>
    0.62
     tendre
    0.56
     amorosa
    0.55
    <h2>
    0.55
     australiano
    0.50
     dentaire
    0.50
    bekistan
    0.49
     mukana
    0.49
    <h3>
    0.48
     letech
    0.48
    Activations Density 1.692%

    No Known Activations