© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13490
    Prev
    Next
    INDEX
    Explanations

    news casts, TV programs, and names of Spanish-speaking people in Panama

    oai_token-act-pair · gemini-2.0-flash

    Foreign language

    np_max-act-logits · gemini-2.0-flash

    say "capitalized" Method used: 2 — tokens after are capitalized/lead with word boundary, so say "capitalized"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     vPvB
    -0.23
     ка
    -0.19
    や
    -0.18
     چ
    -0.16
    ĩnh
    -0.16
     Penh
    -0.16
    gste
    -0.16
     ز
    -0.15
     об
    -0.15
    ghalaya
    -0.15
    POSITIVE LOGITS
     Escuela
    0.58
     avoient
    0.58
     "¡
    0.57
     démocr
    0.57
     kysy
    0.57
     étoit
    0.57
     Fundación
    0.56
     aveug
    0.56
     colorés
    0.56
     spagno
    0.56
    Activations Density 51.155%

    No Known Activations