© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14633
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and constructs that express opinions and analysis of political and sporting events

    oai_token-act-pair · gemini-2.0-flash

    Political victories and winners

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     فريبيس
    -0.59
     agujas
    -0.53
    вый
    -0.49
    importanza
    -0.48
     Fu
    -0.47
    TestBed
    -0.46
     Facing
    -0.46
     présents
    -0.44
    saga
    -0.44
    tibus
    -0.44
    POSITIVE LOGITS
    RectangleBorder
    0.68
    <%@
    0.65
    aarrggbb
    0.61
     "..\..\..\
    0.60
     vPvB
    0.58
    saraba
    0.56
    StateList
    0.55
     vuitton
    0.55
    chyma
    0.55
    terase
    0.54
    Activations Density 2.879%

    No Known Activations