© 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. 17114
    Prev
    Next
    INDEX
    Explanations

    Features: empty()

    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
     உள்
    0.38
    isub
    0.36
     (/
    0.34
     واي
    0.34
     hateful
    0.33
    枝
    0.33
     Evaluation
    0.33
    >|</
    0.33
    fat
    0.32
    િલ
    0.32
    POSITIVE LOGITS
     Dys
    0.42
    Dys
    0.40
     Cri
    0.39
     rises
    0.37
     elapse
    0.37
    アクセ
    0.37
     téléphone
    0.37
     élèves
    0.36
     டிக்க
    0.36
     형성
    0.36
    Activations Density 0.001%

    No Known Activations