© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16029
    Prev
    Next
    INDEX
    Explanations

    the word "peak" and to a lesser extent words associated with looking through something, such as "window"

    oai_token-act-pair · gemini-2.0-flash

    peak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     and
    -0.78
     then
    -0.77
     or
    -0.73
     he
    -0.71
     "
    -0.71
     for
    -0.69
     but
    -0.69
     team
    -0.67
     she
    -0.66
     He
    -0.65
    POSITIVE LOGITS
     ་་
    1.24
     ―――――
    1.16
     Shakspeare
    1.15
     Tartar
    1.06
     Sarm
    1.05
     astral
    1.05
     Courant
    1.05
     Theſe
    1.05
     itſelf
    1.05
     Platon
    1.02
    Activations Density 1.668%

    No Known Activations