© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43435
    Prev
    Next
    INDEX
    Explanations

    high pressure and low pressure

    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_22_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
    ującego
    0.46
    ujący
    0.44
    ردن
    0.44
    逵
    0.42
    اع
    0.39
     responded
    0.38
     pesquis
    0.38
    emente
    0.37
    بات
    0.37
     باع
    0.37
    POSITIVE LOGITS
     hypocrisy
    0.43
     झूठ
    0.42
     ग़
    0.42
    宿
    0.41
    ندی
    0.41
     Babu
    0.40
     hindi
    0.39
     प्रत्येक
    0.39
     बांटा
    0.39
     zero
    0.39
    Activations Density 0.000%

    No Known Activations