© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14792
    Prev
    Next
    INDEX
    Explanations

    section headers

    oai_token-act-pair · gemini-2.0-flash

    Technical/Academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    opardy
    -0.49
    rollers
    -0.48
     therefore
    -0.47
    pers
    -0.47
    IsContent
    -0.47
     thus
    -0.46
    ณ์
    -0.45
    èdia
    -0.45
    mnar
    -0.45
     stood
    -0.43
    POSITIVE LOGITS
     referenties
    0.63
     Roskov
    0.62
     Chriftian
    0.61
    InvalidProtocol
    0.58
    aporation
    0.58
    جمعیت
    0.57
     ſeveral
    0.56
     reaſon
    0.54
     greateſt
    0.54
    تقاوى
    0.54
    Activations Density 0.484%

    No Known Activations