© 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. 14807
    Prev
    Next
    INDEX
    Explanations

    words related to care or familial relationships

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "look"

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

    variations of "look"

    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
     nuage
    -0.57
     متحده
    -0.55
    BagConstraints
    -0.52
    tonsoft
    -0.51
     kasarigan
    -0.50
    **/
    -0.48
    wingen
    -0.48
     matelas
    -0.48
     laude
    -0.48
    boutin
    -0.48
    POSITIVE LOGITS
     look
    2.69
    look
    2.56
     looked
    2.48
     Look
    2.44
     looking
    2.39
     looks
    2.38
    Look
    2.38
    looked
    2.27
     LOOK
    2.27
    LOOK
    2.22
    Activations Density 1.102%

    No Known Activations