© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5819
    Prev
    Next
    INDEX
    Explanations

    verbs indicating past actions or events

    oai_token-act-pair · gemini-2.0-flash

    past tense

    np_max-act · gemini-2.0-flash

    past-tense verbs Method used: 1 — all top tokens are past-tense verbs; explanation: past-tense verbs

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     whoſe
    -0.60
     Hift
    -0.57
    principalColumn
    -0.57
     MaterialApp
    -0.57
    DMETHOD
    -0.52
    agrid
    -0.52
     schwer
    -0.52
     fubject
    -0.51
     SDLK
    -0.51
    बाह
    -0.51
    POSITIVE LOGITS
    <bos>
    1.01
    SourceChecksum
    0.76
     gave
    0.63
     wrote
    0.62
    ’
    0.61
     took
    0.59
    burg
    0.58
    avía
    0.57
     himself
    0.56
     didn
    0.56
    Activations Density 1.460%

    No Known Activations