© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4071
    Prev
    Next
    INDEX
    Explanations

    code snippets and file extensions like `.py`, `.php`, and related keywords like "python", "script", and "sys.", often within the context of web development and scripting.

    oai_token-act-pair · gemini-2.0-flash

    python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     accesso
    -0.55
    +#+
    -0.52
     ComVisible
    -0.49
    else
    -0.46
     partita
    -0.46
    shund
    -0.45
     jak
    -0.45
    EndInit
    -0.45
     immédi
    -0.44
     locali
    -0.44
    POSITIVE LOGITS
    __":
    0.88
    __':
    0.79
     defaultstate
    0.67
    __':
    0.63
    abestanden
    0.60
    TargetException
    0.60
    TagMode
    0.59
    avras
    0.59
    writerow
    0.58
    neſs
    0.57
    Activations Density 2.086%

    No Known Activations