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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10908
    Prev
    Next
    INDEX
    Explanations

    descriptions of a negative work environment

    oai_token-act-pair · gemini-2.0-flash

    work/outside environment

    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
     Environment
    -2.14
    Environment
    -2.09
     environment
    -2.09
     environmental
    -1.97
    environment
    -1.96
     ENVIRONMENT
    -1.95
     environments
    -1.92
    Env
    -1.92
     Environmental
    -1.88
     Environments
    -1.88
    POSITIVE LOGITS
    CloseOperation
    0.69
     الرياضيه
    0.63
     onCancelled
    0.60
    MLLoader
    0.60
    StoryboardSegue
    0.59
    ␮
    0.55
    uyện
    0.55
     porcentual
    0.54
    mobileqq
    0.52
     >=",
    0.51
    Activations Density 1.214%

    No Known Activations