© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12282
    Prev
    Next
    INDEX
    Explanations

    the word "prior," sometimes in conjunction with guilt or other legal terms.

    oai_token-act-pair · gemini-2.0-flash

    prior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     prior
    -0.81
     Prior
    -0.77
    Prior
    -0.72
    prior
    -0.65
    ↵↵
    -0.59
     pri
    -0.55
    <bos>
    -0.54
    Pri
    -0.54
    PRIOR
    -0.52
     Pri
    -0.50
    POSITIVE LOGITS
     myſelf
    0.85
     itſelf
    0.81
     avoient
    0.81
     againſt
    0.78
     himſelf
    0.77
     étoit
    0.77
     ſtill
    0.77
     térmico
    0.76
     ſeveral
    0.76
     pleaſure
    0.76
    Activations Density 0.958%

    No Known Activations