© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4198
    Prev
    Next
    INDEX
    Explanations

    code syntax related to array manipulation but also any mention of size, sort, or division.

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     تضيفلها
    -0.92
     ویکی‌پدیای
    -0.84
    \{\\
    -0.80
    AddTagHelper
    -0.77
    GEBURTSDATUM
    -0.73
    expandindo
    -0.71
     Normdatei
    -0.70
    PerformLayout
    -0.70
     Administrativna
    -0.70
    GraphicsUnit
    -0.69
    POSITIVE LOGITS
    '][]
    0.66
     one
    0.64
    ))^
    0.53
    |')
    0.52
    ']
    0.51
    ']=
    0.51
    "]=
    0.49
    ONES
    0.49
    '=>'
    0.49
    ágot
    0.48
    Activations Density 14.499%

    No Known Activations