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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1607
    Prev
    Next
    INDEX
    Explanations

    opinionated language expressing agreement

    oai_token-act-pair · gemini-2.0-flash

    Abstract nouns regarding relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     complete
    -2.80
     Complete
    -2.64
    complete
    -2.56
    Complete
    -2.48
     COMPLETE
    -2.30
    COMPLETE
    -1.91
     completa
    -1.76
     completo
    -1.59
     complète
    -1.53
     vollständige
    -1.35
    POSITIVE LOGITS
     שוליים
    0.63
    MigrationBuilder
    0.58
    OwnProperty
    0.56
    dymyr
    0.53
     rowspan
    0.52
     Paglinawan
    0.49
     thôi
    0.49
    ligently
    0.48
     referrerpolicy
    0.47
     fièvre
    0.47
    Activations Density 4.501%

    No Known Activations