© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3767
    Prev
    Next
    INDEX
    Explanations

    javascript/typescript imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ~~~~
    0.39
    로그
    0.36
     ?:
    0.36
     आठ
    0.35
    Mais
    0.35
     嗯
    0.35
    列車
    0.34
    ~~~
    0.34
     //'
    0.34
     Ore
    0.33
    POSITIVE LOGITS
    typescript
    0.46
     japonicus
    0.43
    றுத்த
    0.40
    स्थापन
    0.39
     etiology
    0.38
     importing
    0.38
    Albert
    0.38
     torres
    0.38
     expedi
    0.36
    BERT
    0.36
    Activations Density 0.002%

    No Known Activations