© 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. 15149
    Prev
    Next
    INDEX
    Explanations

    clauses beginning with "and"

    oai_token-act-pair · gemini-2.0-flash

    temporal or sequencing words

    np_token-act-pair-logits · gpt-4o-mini
    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
    ruptedException
    -0.78
    #
    -0.77
    EndGlobalSection
    -0.69
    MessageTagHelper
    -0.69
     noqa
    -0.68
    期刊论文
    -0.66
     lyrical
    -0.64
    webElement
    -0.63
     ethnographic
    -0.63
    Rè
    -0.63
    POSITIVE LOGITS
     when
    0.59
     immediately
    0.47
     cuando
    0.47
    when
    0.46
     quando
    0.45
    immediately
    0.44
     continued
    0.42
     bağı
    0.42
     quickly
    0.42
     stopped
    0.42
    Activations Density 1.727%

    No Known Activations