© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3238
    Prev
    Next
    INDEX
    Explanations

    sentences including the word "look" referring to some goal oriented action

    oai_token-act-pair · gemini-2.0-flash

    look

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Looks
    -0.72
     looking
    -0.69
     Looked
    -0.69
     Look
    -0.69
     LOOK
    -0.68
     looks
    -0.66
     Looking
    -0.65
     look
    -0.64
     lookin
    -0.63
    looking
    -0.62
    POSITIVE LOGITS
    randomUUID
    0.56
    djangoproject
    0.55
    ValidationError
    0.54
     didReceive
    0.52
    XmlAccessType
    0.51
     Meksiku
    0.51
    wark
    0.50
    entieth
    0.50
     gynhyrchwyd
    0.49
     désolés
    0.48
    Activations Density 40.614%

    No Known Activations