© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5934
    Prev
    Next
    INDEX
    Explanations

    sentences that mention results, demonstrations, or mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    As

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    SPJ
    -0.59
    ंदीखरीदारी
    -0.52
    .*")]
    -0.48
     出版
    -0.44
    enumii
    -0.44
     <>",
    -0.43
    *~
    -0.43
    >>();
    -0.43
     ویکی‌پدیای
    -0.43
     Consultez
    -0.41
    POSITIVE LOGITS
    stdc
    0.65
     suggested
    0.64
    клопе
    0.63
    AnimationFrame
    0.59
     Suggested
    0.59
    uerre
    0.59
    ESTONE
    0.59
     Vege
    0.58
     Confirmed
    0.58
    sugges
    0.57
    Activations Density 3.332%

    No Known Activations