© 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. 9336
    Prev
    Next
    INDEX
    Explanations

    the phrase "instead of"

    oai_token-act-pair · gemini-2.0-flash

    the word "instead"

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

    instead

    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
    windowFixed
    -1.05
     للاسماء
    -0.86
    ⓧ
    -0.84
     كومونز
    -0.84
    évaluateur
    -0.76
     فريبيس
    -0.76
     وتسجيلات
    -0.76
    SourceChecksum
    -0.74
     estekak
    -0.73
    GTCX
    -0.71
    POSITIVE LOGITS
     of
    1.55
    ของ
    0.80
     của
    0.74
    of
    0.63
     thereof
    0.61
     των
    0.57
     של
    0.56
     του
    0.55
     της
    0.54
     ofthe
    0.52
    Activations Density 4.178%

    No Known Activations