© 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. 13905
    Prev
    Next
    INDEX
    Explanations

    text related to deleting or removing something from a list, document, or device

    oai_token-act-pair · gemini-2.0-flash

    concepts related to removal or deletion

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

    remove

    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
     from
    -0.63
     out
    -0.62
     away
    -0.60
    out
    -0.57
     Away
    -0.50
    from
    -0.49
     aus
    -0.48
     off
    -0.48
    Out
    -0.47
     Remove
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.78
     تضيفلها
    0.69
    principalColumn
    0.68
    BibitemOpen
    0.60
    kaufs
    0.60
     चीज़ों
    0.60
    BibitemShut
    0.59
     postIndex
    0.58
    buttonBar
    0.57
    bibfield
    0.56
    Activations Density 4.205%

    No Known Activations