© 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. 3524
    Prev
    Next
    INDEX
    Explanations

    what looks like Russian and German language fragments

    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
    listdir
    -0.46
    ferential
    -0.45
    deutsche
    -0.45
    binant
    -0.43
    newArrayList
    -0.42
     freie
    -0.41
    FontStyle
    -0.40
    getSystemService
    -0.40
     endwhile
    -0.40
    مره
    -0.40
    POSITIVE LOGITS
     Paglinawan
    0.88
    webElementXpaths
    0.68
    "});
    0.68
    "])
    0.66
    "]];
    0.66
    fromnode
    0.64
     }));
    0.63
    '");
    0.63
     beter
    0.62
     Efq
    0.62
    Activations Density 0.554%

    No Known Activations