© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14298
    Prev
    Next
    INDEX
    Explanations

    words that are strong positive adjectives, or words near strong positive adjectives

    oai_token-act-pair · gemini-2.0-flash

    words related to quality or effort

    np_token-act-pair-logits · gpt-4o-mini

    Positive reviews of creative works

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    onAttach
    -0.55
    Parcelize
    -0.49
    CreateModel
    -0.47
    DockStyle
    -0.47
    randrange
    -0.44
    estacks
    -0.43
    apat
    -0.42
    不然
    -0.42
     ویکی‌پدیا
    -0.42
    ünkü
    -0.41
    POSITIVE LOGITS
     work
    0.86
     stuff
    0.86
     performances
    0.74
    work
    0.73
     Stuff
    0.69
    بوابة
    0.67
    manship
    0.67
     workmanship
    0.66
    stuff
    0.66
     efforts
    0.65
    Activations Density 3.094%

    No Known Activations