© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10641
    Prev
    Next
    INDEX
    Explanations

    the word "laws"

    oai_token-act-pair · gemini-2.0-flash

    laws

    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
    .")
    -1.11
    bibinfo
    -1.06
    )");
    -1.05
    tvguidetime
    -1.04
    
    -1.02
    $")
    -1.02
    */
    -1.01
    !")
    -1.00
    $.
    -0.98
     myſelf
    -0.98
    POSITIVE LOGITS
    tw
    0.72
     conven
    0.65
    nt
    0.64
    en
    0.64
    tes
    0.64
    ten
    0.64
    name
    0.63
    l
    0.63
    t
    0.63
    了
    0.63
    Activations Density 1.371%

    No Known Activations