© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4324
    Prev
    Next
    INDEX
    Explanations

    fragments of sentences in French

    oai_token-act-pair · gemini-2.0-flash

    '

    np_max-act · gemini-2.0-flash

    say "verbs after apostrophe" Method used: 2 — tokens after an apostrophe are French verb forms

    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
     se
    -0.91
    Se
    -0.72
    Попис
    -0.68
     Se
    -0.66
    -------------</
    -0.63
     للمعارف
    -0.63
    izarse
    -0.61
    adpleegd
    -0.61
     haberse
    -0.60
     SE
    -0.59
    POSITIVE LOGITS
    AccessorTable
    0.73
    ocrine
    0.47
    abend
    0.46
    indra
    0.44
    INGTON
    0.43
    inkle
    0.43
    SupportActionBar
    0.43
    ETYPE
    0.42
     käyt
    0.42
    TestingModule
    0.42
    Activations Density 18.550%

    No Known Activations