© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11437
    Prev
    Next
    INDEX
    Explanations

    words joining two statements or setting conditions such as "or", "but", "any", "if", "at"

    oai_token-act-pair · gemini-2.0-flash

    specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     الاطلاع
    -0.72
    новниш
    -0.71
    csolódó
    -0.66
     صوتيه
    -0.65
    grès
    -0.65
    Personendaten
    -0.64
     NUKAT
    -0.63
    ględ
    -0.63
    cửa
    -0.62
     للمعارف
    -0.60
    POSITIVE LOGITS
     fixed
    1.45
     specific
    1.24
    fixed
    1.21
     Fixed
    1.12
    Fixed
    1.09
     Specific
    1.09
    specific
    1.05
     defined
    1.05
     SPECIFIC
    1.04
    Specific
    1.01
    Activations Density 5.206%

    No Known Activations