© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14177
    Prev
    Next
    INDEX
    Explanations

    words that are french or portugese verbs

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash

    fait

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     doing
    -0.87
    doing
    -0.85
     hacer
    -0.84
    Doing
    -0.84
     feito
    -0.78
    Hacer
    -0.76
     Doing
    -0.76
     fait
    -0.75
     faire
    -0.73
     сдела
    -0.73
    POSITIVE LOGITS
     étoient
    0.58
     Efq
    0.57
     étoit
    0.57
     auroit
    0.56
    WEBPACK
    0.56
    BASEPATH
    0.55
    latego
    0.54
     purpoſe
    0.54
     quæ
    0.53
     Récup
    0.52
    Activations Density 14.677%

    No Known Activations