© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3337
    Prev
    Next
    INDEX
    Explanations

    words associated with general negation

    oai_token-act-pair · gemini-2.0-flash

    variants of "either"

    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
    AfterClass
    -0.58
    ">//
    -0.53
    でも
    -0.52
    Etymology
    -0.51
    enddo
    -0.47
    ---*/
    -0.45
     でも
    -0.42
    还会
    -0.42
    Glej
    -0.42
    外部リンク
    -0.41
    POSITIVE LOGITS
     either
    4.00
    either
    3.61
     Either
    3.47
    Either
    3.45
     entweder
    2.94
     enten
    2.20
    ITHER
    2.14
    要么
    2.08
     либо
    1.70
     neither
    1.59
    Activations Density 3.785%

    No Known Activations