© 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. 3879
    Prev
    Next
    INDEX
    Explanations

    the word "category"

    oai_token-act-pair · gemini-2.0-flash

    category

    np_max-act · gemini-2.0-flash

    category

    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_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
    R
    -0.76
    H
    -0.72
    C
    -0.69
    l
    -0.69
    q
    -0.68
    J
    -0.68
    M
    -0.68
    L
    -0.68
    P
    -0.67
    _
    -0.67
    POSITIVE LOGITS
    encils
    1.01
    ratulations
    0.96
    kraine
    0.89
    tinyos
    0.89
    adeloupe
    0.88
    hematical
    0.88
    ourite
    0.85
    riculture
    0.84
    ineſs
    0.81
    ſtanding
    0.81
    Activations Density 2.951%

    No Known Activations