© 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. 13179
    Prev
    Next
    INDEX
    Explanations

    various symbols and keywords associated with programming code, particularly related to variable assignments, function definitions, and boolean logic.

    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
    ժ
    -0.48
     Kette
    -0.46
     Pattaya
    -0.45
    Cy
    -0.45
     Económica
    -0.44
    patch
    -0.44
     Patch
    -0.43
    ise
    -0.43
    MLE
    -0.43
    寿
    -0.43
    POSITIVE LOGITS
    principalColumn
    0.82
    ècie
    0.65
    /*
    0.64
    ⓧ
    0.62
     devenus
    0.60
    zzar
    0.60
    ंदीखरीदारी
    0.59
    Referințe
    0.57
    Ingen
    0.57
    براير
    0.55
    Activations Density 4.171%

    No Known Activations