© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6364
    Prev
    Next
    INDEX
    Explanations

    past tense of "know", or words related to knowledge

    oai_token-act-pair · gemini-2.0-flash

    knew

    np_max-act · gemini-2.0-flash

    knew

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    IContainer
    -0.82
    لينكات
    -0.76
    enerated
    -0.74
    ipheral
    -0.71
     păr
    -0.69
    IBar
    -0.69
    XmlAccessorType
    -0.67
     Majefty
    -0.67
    djangoproject
    -0.66
     Pergamon
    -0.65
    POSITIVE LOGITS
    __':
    0.63
     some
    0.59
    numerusform
    0.57
     the
    0.57
    er
    0.55
    ArgsConstructor
    0.54
    erci
    0.54
    __":
    0.54
     you
    0.54
     שוליים
    0.53
    Activations Density 2.277%

    No Known Activations