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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7823
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to international conflict and social unrest, with a particular emphasis on protests and violence in Muslim countries.

    oai_token-act-pair · gemini-2.0-flash

    news articles / code

    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
     EconPapers
    -0.74
     виправивши
    -0.63
    ruptedException
    -0.63
    thenes
    -0.61
    bolista
    -0.60
    eclared
    -0.60
     Officials
    -0.59
    zzlement
    -0.59
     severance
    -0.57
    setopt
    -0.57
    POSITIVE LOGITS
    الإنجليزية
    0.53
    hoeddwyd
    0.50
    awsze
    0.46
     CreateTagHelper
    0.46
    cshtml
    0.45
    Népesség
    0.45
    unknownFields
    0.43
    endphp
    0.41
    ContentAsync
    0.40
    ulement
    0.39
    Activations Density 16.981%

    No Known Activations