© 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. 8841
    Prev
    Next
    INDEX
    Explanations

    phrases containing verbs like "be" and "may" that express uncertainty or possibility

    oai_token-act-pair · gemini-2.0-flash

    causal relationships or explanations

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

    be

    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
    setVerticalGroup
    -0.57
     nahilalakip
    -0.56
    ArrowToggle
    -0.54
    ViewFeatures
    -0.50
     الحره
    -0.50
    ępnie
    -0.50
    omalainen
    -0.50
    المكان
    -0.49
    ISPR
    -0.49
     resourceCulture
    -0.47
    POSITIVE LOGITS
     because
    0.66
     becauſe
    0.66
    ientí
    0.61
     due
    0.56
    because
    0.56
     becau
    0.55
     greateſt
    0.55
    τέλε
    0.54
    enumi
    0.53
    ]='\
    0.53
    Activations Density 2.352%

    No Known Activations