© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 702
    Prev
    Next
    INDEX
    Explanations

    the phrase "we all know" and similar constructions

    oai_token-act-pair · gemini-2.0-flash

    know

    np_max-act · gemini-2.0-flash

    know

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    rungsseite
    -1.09
     насељу
    -1.03
     Мексичка
    -0.98
    RectangleBorder
    -0.94
    出版年
    -0.93
    ArgsConstructor
    -0.92
     ExecuteAsync
    -0.91
    jooq
    -0.91
    InputBorder
    -0.91
    hdashline
    -0.90
    POSITIVE LOGITS
     
    0.58
    ,
    0.49
    <bos>
    0.46
    ↵↵
    0.45
    -
    0.42
     the
    0.42
     to
    0.41
    (
    0.41
    ↵
    0.40
     “
    0.40
    Activations Density 0.993%

    No Known Activations