© 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. 2615
    Prev
    Next
    INDEX
    Explanations

    words or phrases that indicate government, laws, or policy

    oai_token-act-pair · gemini-2.0-flash

    gibberish

    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
    have
    -2.16
     have
    -2.16
    Have
    -2.09
     Have
    -2.05
     HAVE
    -1.80
    HAVE
    -1.75
     hebben
    -1.33
     haben
    -1.29
     hav
    -1.20
     έχουν
    -1.13
    POSITIVE LOGITS
    تقاوى
    0.92
    出版年
    0.89
     createState
    0.75
    XmlAccessType
    0.75
    новништво
    0.72
    PerformLayout
    0.72
     nahilalakip
    0.71
    antMatchers
    0.70
    AutoScaleMode
    0.69
    elemField
    0.69
    Activations Density 20.470%

    No Known Activations