© 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. 12330
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate comparison or instruction.

    oai_token-act-pair · gemini-2.0-flash

    as

    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
    ChildScrollView
    -0.71
     Signalez
    -0.68
     createSprite
    -0.68
    sizeCache
    -0.68
     disambiguazione
    -0.62
    transQ
    -0.58
     resourceCulture
    -0.58
    SafeMath
    -0.57
    lectricité
    -0.57
    libft
    -0.55
    POSITIVE LOGITS
     per
    3.66
    per
    2.55
    Per
    2.45
     Per
    2.44
     PER
    2.08
    PER
    1.78
     пер
    1.13
    PerPage
    1.10
    perin
    1.05
    パー
    1.05
    Activations Density 3.579%

    No Known Activations