© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12785
    Prev
    Next
    INDEX
    Explanations

    sentences about peoples' money troubles, especially with regards to taxes and agreements

    oai_token-act-pair · gemini-2.0-flash

    Refusal and Neglect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    extAlignment
    -0.77
    tonode
    -0.74
    InputBorder
    -0.71
     BoxDecoration
    -0.67
    TintMode
    -0.64
     متعلقه
    -0.64
     MainAxisSize
    -0.64
    ValueStyle
    -0.64
    rungsseite
    -0.63
    poptosis
    -0.63
    POSITIVE LOGITS
     ignoring
    0.93
     refusal
    0.92
     avoidance
    0.91
     refusing
    0.91
     neglect
    0.91
     avoiding
    0.90
     ignore
    0.88
     refuse
    0.87
     refuses
    0.81
     neglecting
    0.81
    Activations Density 4.133%

    No Known Activations