© 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. 10742
    Prev
    Next
    INDEX
    Explanations

    conditional statements (if, else) and some keywords linked to object-oriented programming such as self, new, and value

    oai_token-act-pair · gemini-2.0-flash

    else

    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
    <bos>
    -1.01
     magique
    -0.80
    AddHtmlAttribute
    -0.72
     فريبيس
    -0.72
    StoryboardSegue
    -0.69
     للمعارف
    -0.67
     صوتيه
    -0.66
     Monfieur
    -0.66
     ویکی‌پدی
    -0.65
     sauvage
    -0.63
    POSITIVE LOGITS
    enumi
    0.66
     оригіналу
    0.50
    ospor
    0.49
    ……
    0.49
     sil
    0.48
     mekan
    0.48
    хани
    0.47
     Reporter
    0.47
    glEnd
    0.46
    FFIX
    0.46
    Activations Density 0.715%

    No Known Activations