© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 6006
    Prev
    Next
    INDEX
    Explanations

    words referring to analysis, study, or data collection

    oai_token-act-pair · gemini-2.0-flash

    say "of"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    windowFixed
    -0.69
    menea
    -0.68
    +#+#
    -0.65
    chengladbach
    -0.65
    ſelf
    -0.63
    ه‌اند
    -0.63
    Geografía
    -0.61
     Cæsar
    -0.61
    ormick
    -0.60
    isburg
    -0.59
    POSITIVE LOGITS
     of
    1.81
    of
    0.91
     của
    0.89
    ของ
    0.77
    Of
    0.68
     Of
    0.66
    オブ
    0.58
     των
    0.57
    tof
    0.55
     OF
    0.54
    Activations Density 2.596%

    No Known Activations