© 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. 13151
    Prev
    Next
    INDEX
    Explanations

    abbreviations for medical concepts and words related to stress and educational levels

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'U'

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

    The letter U

    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
    bt
    -0.45
    ้ม
    -0.41
    erto
    -0.40
     хо
    -0.39
    rige
    -0.39
    ört
    -0.38
    zew
    -0.37
    出版年
    -0.37
    latego
    -0.37
    cv
    -0.37
    POSITIVE LOGITS
     U
    1.01
     UA
    0.99
     UP
    0.97
     UL
    0.96
     United
    0.94
    UP
    0.93
     UO
    0.92
     Utd
    0.90
     UR
    0.90
    United
    0.90
    Activations Density 3.058%

    No Known Activations