© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11348
    Prev
    Next
    INDEX
    Explanations

    words containing the "able" suffix, or that start with "flus" like flush"

    oai_token-act-pair · gemini-2.0-flash

    swit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    autoreleasepool
    -0.49
    CppCodeGen
    -0.47
     luk
    -0.47
    databind
    -0.45
    Hochspringen
    -0.45
    twimg
    -0.44
    fastjson
    -0.44
    annu
    -0.43
    viers
    -0.42
    AddTagHelper
    -0.42
    POSITIVE LOGITS
    sh
    0.71
    chowa
    0.69
    ah
    0.68
    h
    0.68
    TintMode
    0.68
     chì
    0.67
    tvguidetime
    0.66
    ｈ
    0.66
    Sh
    0.66
    vh
    0.65
    Activations Density 1.640%

    No Known Activations