© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12470
    Prev
    Next
    INDEX
    Explanations

    the word "critical" along with related terms in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    the term 'critical'

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

    critical

    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
    Personendaten
    -0.88
    featureID
    -0.76
    addCriterion
    -0.76
    MigrationBuilder
    -0.76
    numerusform
    -0.75
    EDEFAULT
    -0.73
    PreferredItem
    -0.72
    Datuak
    -0.72
    RTEE
    -0.72
     ―――――
    -0.71
    POSITIVE LOGITS
    ɲ
    0.59
    ity
    0.58
    sed
    0.54
    iglia
    0.50
    raise
    0.46
    帖最后由
    0.46
     sanitarios
    0.46
     d
    0.45
     rise
    0.44
    ansible
    0.43
    Activations Density 1.934%

    No Known Activations