© 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. 7908
    Prev
    Next
    INDEX
    Explanations

    the word "bad" and related words like "dreadful."

    oai_token-act-pair · gemini-2.0-flash

    negative descriptors with variations of "bad"

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

    bad

    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
    -0.73
     ainfi
    -0.64
    CloseHandle
    -0.64
     générations
    -0.63
     puissiez
    -0.62
    apimachinery
    -0.61
     étoit
    -0.60
    Documento
    -0.60
     recevrez
    -0.60
     feroit
    -0.60
    POSITIVE LOGITS
    gered
    0.54
    gering
    0.52
    ContentAsync
    0.51
    inage
    0.51
     rap
    0.48
    BorderFactory
    0.47
    <!--[
    0.44
    rap
    0.43
     habits
    0.43
    gulp
    0.43
    Activations Density 0.797%

    No Known Activations