© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6416
    Prev
    Next
    INDEX
    Explanations

    positive words related to hobbies and social life

    oai_token-act-pair · gemini-2.0-flash

    better

    np_max-act-logits · gemini-2.0-flash

    say "comparative words"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    astify
    -0.56
     nonatomic
    -0.52
    bootstrapcdn
    -0.47
     obstante
    -0.45
    кипе
    -0.43
    addCriterion
    -0.43
    fromCharCode
    -0.42
    (;;)
    -0.42
     ExecuteAsync
    -0.42
     kháng
    -0.41
    POSITIVE LOGITS
     better
    1.51
    better
    1.23
     mejor
    1.19
     melhor
    1.12
     best
    1.09
     BETTER
    1.06
     mieux
    1.06
     meglio
    1.04
     bättre
    1.03
     besser
    1.01
    Activations Density 3.107%

    No Known Activations