© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4351
    Prev
    Next
    INDEX
    Explanations

    extended phrases that include "for life", "friends", or court sentences

    oai_token-act-pair · gemini-2.0-flash

    the concept of "life"

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

    life

    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
    ỡng
    -0.47
    uscht
    -0.46
    üns
    -0.43
    Cách
    -0.43
    pexpr
    -0.42
    tics
    -0.40
    itamos
    -0.40
    ostar
    -0.39
    ho
    -0.39
    ApiOperation
    -0.39
    POSITIVE LOGITS
     life
    3.06
     Life
    2.58
    life
    2.56
     LIFE
    2.47
    Life
    2.45
    LIFE
    2.34
     lifetime
    2.00
     vida
    1.95
     lif
    1.86
     Leben
    1.84
    Activations Density 1.485%

    No Known Activations