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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9660
    Prev
    Next
    INDEX
    Explanations

    language related to asking for forgiveness and admitting wrongdoing

    oai_token-act-pair · 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
     compensation
    -1.95
     compens
    -1.84
     compensating
    -1.81
     compensated
    -1.80
     apology
    -1.78
     Compensation
    -1.77
     Compens
    -1.77
    compensation
    -1.74
    compens
    -1.73
    Compensation
    -1.71
    POSITIVE LOGITS
    ọc
    0.52
    Хьажоргаш
    0.52
    jsonwebtoken
    0.48
     Larkin
    0.47
    Filmographie
    0.46
    期刊论文
    0.46
    aronder
    0.46
    getElement
    0.46
    INTR
    0.45
    textAppearance
    0.45
    Activations Density 5.229%

    No Known Activations