© 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. 10366
    Prev
    Next
    INDEX
    Explanations

    words related to aviation and the Wright brothers

    oai_token-act-pair · gemini-2.0-flash

    terms related to flight

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

    flying

    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
     MainAxisSize
    -0.92
    脚注の使い方
    -0.91
    AndEndTag
    -0.90
    +#+#
    -0.87
     كومونز
    -0.83
    دانشنامهٔ
    -0.77
     snippetHide
    -0.76
     يتيمه
    -0.75
     للمعارف
    -0.74
    rungsseite
    -0.72
    POSITIVE LOGITS
     flying
    1.97
     flight
    1.78
     flown
    1.73
     flew
    1.66
     fly
    1.66
    flying
    1.65
    Flying
    1.55
     flights
    1.55
     Flying
    1.53
     Flight
    1.49
    Activations Density 4.583%

    No Known Activations