© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14179
    Prev
    Next
    INDEX
    Explanations

    words, parts of words, and codes that don't seem to have much connection to each other

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Geplaatst
    -0.76
     صوتيه
    -0.69
    WriteTagHelper
    -0.63
    __((
    -0.61
    ArrowToggle
    -0.61
    InputTagHelper
    -0.59
     poveznice
    -0.58
    MessageOf
    -0.58
    :+:
    -0.58
    setVerticalGroup
    -0.58
    POSITIVE LOGITS
     meille
    0.56
    ltä
    0.54
    paikan
    0.51
     particulières
    0.50
     spéciaux
    0.48
    bka
    0.47
     lợi
    0.47
     käytet
    0.47
     beteken
    0.46
    rąg
    0.45
    Activations Density 9.774%

    No Known Activations