© 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. 3463
    Prev
    Next
    INDEX
    Explanations

    instances of someone giving another person a negative or judgemental look

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "look"

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

    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
     Pasal
    -0.48
    djangoproject
    -0.45
    fromnode
    -0.44
    getDoctrine
    -0.43
    Joined
    -0.42
    ztat
    -0.42
     مشين
    -0.39
     aman
    -0.38
    Abitanti
    -0.38
     biên
    -0.38
    POSITIVE LOGITS
     look
    1.02
     looks
    1.01
    look
    0.97
     looking
    0.96
     LOOK
    0.93
    Look
    0.91
     Look
    0.91
    looking
    0.91
    looks
    0.88
     looked
    0.85
    Activations Density 1.242%

    No Known Activations