© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11402
    Prev
    Next
    INDEX
    Explanations

    a combination of German, Javascript tags and code snippets, words related to connections, and conversational discourse

    oai_token-act-pair · gemini-2.0-flash

    Internet contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     pla
    -0.46
     Hamma
    -0.45
     Cornell
    -0.45
     Magal
    -0.43
     patro
    -0.42
     Pla
    -0.40
    lossal
    -0.40
     Soria
    -0.39
    Cornell
    -0.39
    principle
    -0.39
    POSITIVE LOGITS
     kaarangay
    0.95
    Personendaten
    0.93
    帖最后由
    0.89
    MENAFN
    0.82
     kasarigan
    0.80
    SuccessListener
    0.80
    __":
    0.79
     الحره
    0.78
    Jereo
    0.77
     >=",
    0.76
    Activations Density 0.546%

    No Known Activations