© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12581
    Prev
    Next
    INDEX
    Explanations

    words relating to months, weeks, and annual events

    oai_token-act-pair · gemini-2.0-flash

    annual

    np_max-act · gemini-2.0-flash

    annual

    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_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     snippetHide
    -0.88
    Personensuche
    -0.83
    principalColumn
    -0.81
    Autoritní
    -0.76
    setVerticalGroup
    -0.75
    TagMode
    -0.75
    MemoryWarning
    -0.74
    parsedMessage
    -0.74
    +:+
    -0.72
     Савезне
    -0.72
    POSITIVE LOGITS
     annual
    0.60
     Annual
    0.56
    Annual
    0.55
     anual
    0.52
    ográficas
    0.48
    annual
    0.48
    ↵↵
    0.47
     pourtant
    0.47
     traditionnel
    0.45
     yearly
    0.44
    Activations Density 0.733%

    No Known Activations