© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6616
    Prev
    Next
    INDEX
    Explanations

    different forms of seeing or noticing

    oai_token-act-pair · gemini-2.0-flash

    French language fragments

    np_max-act · gemini-2.0-flash

    see

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    istoitu
    -0.56
    CompleteListener
    -0.54
    -------
    -0.51
    intree
    -0.50
    mander
    -0.49
    lorette
    -0.49
    Anhalt
    -0.48
     Riemann
    -0.47
    WithIOException
    -0.47
    ništvo
    -0.46
    POSITIVE LOGITS
     seeing
    1.78
     sees
    1.77
     saw
    1.73
     seen
    1.67
     see
    1.63
    seeing
    1.51
     Seeing
    1.45
    Seeing
    1.41
     Sees
    1.37
    seen
    1.36
    Activations Density 0.637%

    No Known Activations