© 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. 11724
    Prev
    Next
    INDEX
    Explanations

    language indicating someone is stating their opinion to defend a position

    oai_token-act-pair · gemini-2.0-flash

    defense/defending

    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
    iség
    -0.50
    breo
    -0.48
    UrlResolution
    -0.48
    usermodel
    -0.48
    droje
    -0.47
    ADOW
    -0.47
    iedy
    -0.46
    nowu
    -0.46
    prnewswire
    -0.45
    ]")]
    -0.45
    POSITIVE LOGITS
     defense
    2.61
     defence
    2.47
     defend
    2.09
    defense
    2.05
     Defense
    2.00
    Defense
    2.00
     defending
    1.96
     defended
    1.95
     defenses
    1.91
     defends
    1.91
    Activations Density 3.134%

    No Known Activations