© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14397
    Prev
    Next
    INDEX
    Explanations

    Six Sigma process control

    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_34_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
     oblong
    0.37
    кости
    0.37
    𝒽
    0.37
     సహాయ
    0.36
    জায়
    0.35
     Maxim
    0.34
     secreted
    0.34
     refrigeration
    0.34
     самую
    0.34
     ಕೋ
    0.34
    POSITIVE LOGITS
     Six
    0.41
    croll
    0.39
    Six
    0.38
    ijl
    0.38
    𝐗
    0.38
    prevent
    0.38
    ផ្នែក
    0.37
    spawn
    0.37
     ஆயிரம்
    0.37
     spawn
    0.36
    Activations Density 0.035%

    No Known Activations