© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8945
    Prev
    Next
    INDEX
    Explanations

    the phrase "you're right."

    oai_token-act-pair · gemini-2.0-flash

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ventura
    -0.51
    IndentedString
    -0.50
    gráfico
    -0.49
    cery
    -0.46
    vents
    -0.46
    gren
    -0.46
     brancas
    -0.45
    버
    -0.44
     Pil
    -0.44
    IBU
    -0.44
    POSITIVE LOGITS
    клопе
    0.63
     للاسماء
    0.61
    Toponymie
    0.59
    tvguidetime
    0.59
    المشاركات
    0.58
     orologio
    0.57
    mybatisplus
    0.57
    ETING
    0.57
    nloa
    0.57
    Spam
    0.57
    Activations Density 1.222%

    No Known Activations