© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15571
    Prev
    Next
    INDEX
    Explanations

    mentions of crowds or waiting

    oai_token-act-pair · gemini-2.0-flash

    terms related to online content and subscriptions

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

    restaurant and travel experiences

    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
    Negative Logits
    OGND
    -0.70
    BagConstraints
    -0.66
    RuleContext
    -0.63
     ProtoMessage
    -0.61
    Hochspringen
    -0.59
     obstructed
    -0.59
     motherhood
    -0.56
    itinéraire
    -0.56
    tagHelperRunner
    -0.56
    DispatchToProps
    -0.56
    POSITIVE LOGITS
     internetowa
    0.46
    patreon
    0.46
     réservé
    0.43
    liggende
    0.43
    ChildScrollView
    0.42
    teady
    0.41
    <bos>
    0.41
    iterraneo
    0.40
     Fit
    0.40
    SpringBootTest
    0.40
    Activations Density 1.782%

    No Known Activations