© 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. 12003
    Prev
    Next
    INDEX
    Explanations

    patterns or actions that are repetitious

    oai_token-act-pair · gemini-2.0-flash

    repetition

    np_max-act · gemini-2.0-flash
    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
    Repeat
    -1.07
     repetir
    -1.05
     repeat
    -1.04
     Repeat
    -1.04
    repeat
    -1.03
     répé
    -0.97
     repeating
    -0.97
     repeated
    -0.94
     repetition
    -0.92
     ripet
    -0.91
    POSITIVE LOGITS
    ادث
    0.48
     Seeb
    0.48
     provisional
    0.48
    ersdorf
    0.48
     notices
    0.47
     bod
    0.46
    irsten
    0.45
    hies
    0.44
     tentative
    0.44
     premium
    0.44
    Activations Density 12.728%

    No Known Activations