© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3445
    Prev
    Next
    INDEX
    Explanations

    words or phrases that express negativity, denial, or refutation, often within the context of falsehoods, problems, or strong disagreement.

    oai_token-act-pair · gemini-2.0-flash

    falsehoods, lies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    WebElementEntity
    -0.50
    oredCriteria
    -0.46
    ValueGeneration
    -0.44
    IntentFilter
    -0.44
    cker
    -0.44
    RenderAtEndOf
    -0.44
    χύ
    -0.43
     Schein
    -0.43
    pote
    -0.42
    paign
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.65
     diſt
    0.60
    MessageOf
    0.59
     ModelExpression
    0.59
    Tembelea
    0.59
     समीक्षक
    0.58
     ſeveral
    0.58
     ſmall
    0.57
    viewDidLoad
    0.57
    ,:);
    0.57
    Activations Density 2.605%

    No Known Activations