Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6097
    Prev
    Next
    INDEX
    Explanations

    legal and historical documents that reference marriage and death

    oai_token-act-pair · gemini-2.0-flash

    terms related to divorce and separation

    np_token-act-pair-logits · gpt-4o-mini

    divorce/separation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    posób
    -0.59
    хьтан
    -0.56
    脚注の使い方
    -0.56
    horabuena
    -0.55
    Pranala
    -0.48
    帖最后由
    -0.48
    ACGIH
    -0.46
    neurial
    -0.46
    DoubleQuotes
    -0.45
     sourire
    -0.44
    POSITIVE LOGITS
     break
    0.63
     broken
    0.62
    DIV
    0.61
     breaks
    0.60
     divorce
    0.60
    Ecotoxicity
    0.59
    Break
    0.58
     Divorce
    0.58
    Arr
    0.58
    div
    0.58
    Activations Density 1.787%

    No Known Activations