© 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. 7063
    Prev
    Next
    INDEX
    Explanations

    words related to organized meetings and political gatherings

    oai_token-act-pair · gemini-2.0-flash

    words related to conferences or formal events

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

    organized events

    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
    ########.
    -0.57
    TagMode
    -0.50
    ly
    -0.48
    makeConstraints
    -0.45
    SOUNDBITE
    -0.44
    Gambas
    -0.43
    :✨
    -0.43
     nakalista
    -0.43
     cento
    -0.42
    χρι
    -0.42
    POSITIVE LOGITS
    RectangleBorder
    0.72
    rungsseite
    0.62
    StoryboardSegue
    0.57
     noqa
    0.54
    enschaften
    0.54
    DockStyle
    0.53
    Бахар
    0.53
     écoulé
    0.53
    balleur
    0.53
    NUMX
    0.52
    Activations Density 5.473%

    No Known Activations