© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12156
    Prev
    Next
    INDEX
    Explanations

    C/C++ header include statements

    oai_token-act-pair · gemini-2.0-flash

    h

    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
    ::
    -0.45
    p
    -0.42
    t
    -0.42
    ;
    -0.39
    ற்று
    -0.39
    j
    -0.36
    Хро
    -0.36
    iti
    -0.36
    mergeFrom
    -0.35
     сил
    -0.35
    POSITIVE LOGITS
     يتيمه
    1.00
     فريبيس
    0.90
     مشين
    0.85
    kloped
    0.84
     resourceCulture
    0.83
     Houſe
    0.81
    Hochspringen
    0.80
    ksikon
    0.79
    tableFuture
    0.79
    Rhestr
    0.76
    Activations Density 1.477%

    No Known Activations