© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14753
    Prev
    Next
    INDEX
    Explanations

    the phrase 'reasons why'

    oai_token-act-pair · gemini-2.0-flash

    why

    np_max-act · gemini-2.0-flash
    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
    sizeCache
    -1.06
     rospy
    -0.94
    AccessorTable
    -0.92
     "..\..\..\
    -0.90
     дописавши
    -0.90
    tvguidetime
    -0.89
     Vikipedi
    -0.89
    ьаж
    -0.89
    ThroughAttribute
    -0.88
     itſelf
    -0.88
    POSITIVE LOGITS
    nes
    0.60
    4
    0.57
    $
    0.57
     Glorious
    0.56
    n
    0.56
    r
    0.56
    nis
    0.55
    ↵
    0.55
    led
    0.54
    ser
    0.54
    Activations Density 1.314%

    No Known Activations