© 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. 12356
    Prev
    Next
    INDEX
    Explanations

    code and configuration file snippets

    oai_token-act-pair · gemini-2.0-flash

    "*/"

    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
     MainAxisSize
    -0.67
     الحره
    -0.66
     raiſ
    -0.60
    styleUrls
    -0.60
    ſelves
    -0.59
     poffible
    -0.58
    ſelf
    -0.58
    原始内容存档于
    -0.58
    (!_
    -0.57
     curé
    -0.57
    POSITIVE LOGITS
    grab
    0.55
    queryInterface
    0.54
     Plate
    0.53
     geçir
    0.53
     Вікі
    0.52
    Nave
    0.51
     ग्राहक
    0.51
    хьтан
    0.51
    PYX
    0.51
    Reach
    0.50
    Activations Density 9.592%

    No Known Activations