© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13647
    Prev
    Next
    INDEX
    Explanations

    the word "safe" (sometimes with surrounding words)

    oai_token-act-pair · gemini-2.0-flash

    instances of the word "safe"

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

    safe

    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
     tốt
    -0.52
     beste
    -0.50
    celot
    -0.50
     effective
    -0.49
     great
    -0.48
     mejores
    -0.48
     better
    -0.48
     optimally
    -0.47
     excellent
    -0.46
     meilleurs
    -0.46
    POSITIVE LOGITS
     mergeFrom
    0.76
    AccessorTable
    0.65
    ⓧ
    0.63
     GenerationType
    0.62
    jspb
    0.60
    expandindo
    0.60
    annica
    0.60
    oredCriteria
    0.54
     nahilalakip
    0.54
     للاسماء
    0.53
    Activations Density 1.751%

    No Known Activations