© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13108
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods or measures

    oai_token-act-pair · gemini-2.0-flash

    time

    np_max-act · gemini-2.0-flash

    season

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    SharedDtor
    -0.56
     morning
    -0.56
    onta
    -0.52
     week
    -0.51
    modelBuilder
    -0.50
    TRIBUN
    -0.50
     day
    -0.50
    épend
    -0.49
     للاسماء
    -0.49
    principalTable
    -0.48
    POSITIVE LOGITS
     FileInputStream
    0.57
    horesis
    0.53
    Neighbors
    0.52
    áky
    0.51
     Bricks
    0.51
    Awe
    0.50
    Exited
    0.50
     consultato
    0.50
    Kako
    0.50
    Обу
    0.50
    Activations Density 3.090%

    No Known Activations