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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5977
    Prev
    Next
    INDEX
    Explanations

    text discussing lies or falseness and truth, especially in the context of politics

    oai_token-act-pair · gemini-2.0-flash

    false

    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
     (
    -0.68
     utilize
    -0.57
    true
    -0.55
     and
    -0.54
    <em>
    -0.54
    ↵
    -0.52
     true
    -0.52
    phazard
    -0.52
    enqueue
    -0.51
     utilizing
    -0.50
    POSITIVE LOGITS
    <bos>
    0.98
     مشين
    0.86
    الحياه
    0.85
     CiNii
    0.84
    rungsseite
    0.84
     ſche
    0.83
     avoient
    0.82
     étoit
    0.81
     ſeveral
    0.81
     auroit
    0.81
    Activations Density 3.416%

    No Known Activations