© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    descriptive verbs and phrases related to opinions, analysis, and judgement.

    oai_token-act-pair · gemini-2.0-flash

    questions and explanations

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

    explain/demonstrate

    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
    verwijspagina
    -0.74
     nahilalakip
    -0.60
     onCancelled
    -0.58
    oughby
    -0.57
     noqa
    -0.55
    setViewportView
    -0.55
    saurus
    -0.54
    jooq
    -0.54
    estroying
    -0.54
     cherchés
    -0.52
    POSITIVE LOGITS
     how
    1.16
     why
    0.87
     what
    0.85
     who
    0.79
    how
    0.72
     HOW
    0.68
    why
    0.63
     to
    0.62
     the
    0.60
     hvordan
    0.60
    Activations Density 4.867%

    No Known Activations