© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12636
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to argumentation and reasoning.

    oai_token-act-pair · gemini-2.0-flash

    lie/lies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ModelExpression
    -0.70
    +#+
    -0.59
    ButterKnife
    -0.57
     يتيمه
    -0.53
    tagHelper
    -0.52
     تعدى
    -0.52
     xmlns
    -0.51
    tización
    -0.50
    irmingham
    -0.48
    Rhestr
    -0.48
    POSITIVE LOGITS
     lie
    2.94
     lies
    2.77
     lying
    2.59
     Lying
    2.22
    Lying
    2.19
     LIE
    2.11
     Lies
    2.02
     Lie
    1.98
    lying
    1.97
    Lie
    1.91
    Activations Density 6.713%

    No Known Activations