© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11774
    Prev
    Next
    INDEX
    Explanations

    the word "not," sometimes in the context of "whether or not."

    oai_token-act-pair · gemini-2.0-flash

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    moiselle
    -1.03
     Majefty
    -1.02
     ―――――
    -1.02
     **/
    -0.98
    berdayakan
    -0.98
     pleaſure
    -0.98
     leſs
    -0.97
    ^(@)
    -0.97
     ་་
    -0.97
    ſelves
    -0.96
    POSITIVE LOGITS
    <bos>
    0.76
    .
    0.65
    ,
    0.63
    o
    0.63
    providedIn
    0.61
     
    0.60
    (
    0.58
    i
    0.54
    ’
    0.54
     and
    0.53
    Activations Density 0.428%

    No Known Activations