© 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. 15169
    Prev
    Next
    INDEX
    Explanations

    words associated with legal, commercial or political power

    oai_token-act-pair · gemini-2.0-flash

    words ending in 'ed'

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

    say "ed"

    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
    DockStyle
    -0.89
    tvguidetime
    -0.77
     المعيارى
    -0.72
    참고
    -0.72
    ImageContext
    -0.71
     AspNetCore
    -0.68
    RenderAtEndOf
    -0.67
    webElement
    -0.61
     Signalez
    -0.61
     cherchés
    -0.61
    POSITIVE LOGITS
    ed
    1.16
    ted
    0.99
    ned
    0.96
    sed
    0.92
    ied
    0.90
    ered
    0.88
    ED
    0.88
    ened
    0.84
     ed
    0.83
    ded
    0.82
    Activations Density 2.104%

    No Known Activations