© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 89
    Prev
    Next
    INDEX
    Explanations

    language common to legal documents about disability claims

    oai_token-act-pair · gemini-2.0-flash

    Social programs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AddTagHelper
    -0.95
     sosial
    -0.89
    social
    -0.88
    ArrowToggle
    -0.87
    Social
    -0.87
    TagHelpers
    -0.86
     Sociales
    -0.84
     Social
    -0.82
     social
    -0.82
     الاجتماعية
    -0.81
    POSITIVE LOGITS
     mean
    0.36
    السكان
    0.36
    Overflow
    0.34
    เร็ว
    0.34
    的能力
    0.34
    me
    0.34
    یی
    0.33
    ीक
    0.33
    astu
    0.33
     ind
    0.33
    Activations Density 2.118%

    No Known Activations