© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6336
    Prev
    Next
    INDEX
    Explanations

    mentions of types of cancer.

    oai_token-act-pair · gemini-2.0-flash

    cancer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     InputDecoration
    -0.81
    клопе
    -0.79
    getMenuInflater
    -0.75
    ]--;
    -0.74
     سكانية
    -0.69
     Administrativna
    -0.68
     betweenstory
    -0.67
     mohair
    -0.64
    SharedCtor
    -0.64
    drawal
    -0.64
    POSITIVE LOGITS
    AddressBook
    0.45
    kháu
    0.44
    Writable
    0.42
    암
    0.42
     Mal
    0.41
    homa
    0.41
    blast
    0.40
    mal
    0.40
    ガン
    0.40
    سر
    0.39
    Activations Density 0.838%

    No Known Activations