© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12543
    Prev
    Next
    INDEX
    Explanations

    references to "we," "us," "them", instructions, rules, and beliefs.

    oai_token-act-pair · gemini-2.0-flash

    pronouns referencing people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     '\\;'
    -0.85
    setVerticalGroup
    -0.79
    SourceChecksum
    -0.79
    aarrggbb
    -0.73
    ThroughAttribute
    -0.72
    MigrationBuilder
    -0.70
     thiệu
    -0.68
     ostavi
    -0.68
     Taktlose
    -0.67
     NSCoder
    -0.66
    POSITIVE LOGITS
     themselves
    0.46
    Hozzáférés
    0.46
     الاطلاع
    0.44
     nasel
    0.40
    atisch
    0.39
     herself
    0.38
     elle
    0.36
     snatch
    0.35
     Mine
    0.35
     relatively
    0.35
    Activations Density 3.380%

    No Known Activations