© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4337
    Prev
    Next
    INDEX
    Explanations

    snippets of code, especially in C-like languages or mathematical notations, and potentially also text related to legal matters and work environments.

    oai_token-act-pair · gemini-2.0-flash

    code-related texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    EndInit
    -0.53
     setuptools
    -0.49
    ArrowToggle
    -0.49
    참고
    -0.48
    <bos>
    -0.46
    LEncoder
    -0.45
     Arhivirano
    -0.44
     Besøkt
    -0.44
    razor
    -0.43
    TextSpan
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.82
    DockStyle
    0.76
     فريبيس
    0.61
     gynhyrchwyd
    0.60
    IntoConstraints
    0.60
    Autoritní
    0.58
    EndGlobalSection
    0.58
     utafitiHapana
    0.57
    olkata
    0.57
     CreateTagHelper
    0.57
    Activations Density 26.120%

    No Known Activations