© 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. 331
    Prev
    Next
    INDEX
    Explanations

    text about US foreign policy and interventionism

    oai_token-act-pair · gemini-2.0-flash

    political/historical contexts

    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
     saites
    -0.63
    GenerationType
    -0.57
    MockMvc
    -0.53
    دانشنامهٔ
    -0.52
    הערות
    -0.49
    DeleteBehavior
    -0.48
    HasKey
    -0.47
    joc
    -0.47
    huan
    -0.46
    webElementXpaths
    -0.46
    POSITIVE LOGITS
    ttemberg
    0.51
    uxxxx
    0.51
     bandeira
    0.50
     fédé
    0.50
     resultMap
    0.50
    usahaan
    0.49
     Finlande
    0.49
     récomp
    0.48
    ظهار
    0.48
    StartTag
    0.47
    Activations Density 9.932%

    No Known Activations