© 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. 4419
    Prev
    Next
    INDEX
    Explanations

    numbers, money, and financial terms and references

    oai_token-act-pair · gemini-2.0-flash

    large/good

    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
     ContentValues
    -0.71
    ContentAlignment
    -0.69
    TagMode
    -0.64
    SequentialGroup
    -0.60
     Ment
    -0.59
     Pren
    -0.57
    nonatomic
    -0.56
     Self
    -0.56
     VOW
    -0.56
    VersionUID
    -0.54
    POSITIVE LOGITS
     Great
    0.84
     Big
    0.73
    Great
    0.73
    PerformLayout
    0.69
    Big
    0.66
     Massive
    0.63
     Good
    0.63
    RTDA
    0.59
     Terrible
    0.57
     Wins
    0.56
    Activations Density 9.419%

    No Known Activations