© 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. 5101
    Prev
    Next
    INDEX
    Explanations

    text in languages other than English, especially those with right-to-left scripts and Japanese

    oai_token-act-pair · gemini-2.0-flash

    Assorted text

    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
    ization
    -0.43
    isation
    -0.41
     strategy
    -0.38
     technique
    -0.37
     boste
    -0.37
    كويكب
    -0.37
     audit
    -0.36
     efficiency
    -0.36
     producti
    -0.35
    ized
    -0.35
    POSITIVE LOGITS
    存于互联网档案馆
    0.84
     defaultstate
    0.80
    VersionUID
    0.76
    MigrationBuilder
    0.75
    ResumeLayout
    0.75
    DataAnnotations
    0.74
    makeText
    0.74
    onAttach
    0.73
    invokeLater
    0.73
    migrationBuilder
    0.73
    Activations Density 3.766%

    No Known Activations