© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34955
    Prev
    Next
    INDEX
    Explanations

    estate, development, search, legal, wholesale, implementation, cleaning

    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_31_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
     cafeter
    0.38
     transferee
    0.34
    Excluded
    0.33
     monotone
    0.32
    _=
    0.32
     மணிக்கு
    0.32
     બંને
    0.32
     FLU
    0.32
     geologist
    0.32
     훨
    0.31
    POSITIVE LOGITS
    <start_of_image>
    0.33
     mkdir
    0.33
    Aw
    0.33
     chia
    0.32
    ya
    0.29
     Po
    0.29
     supervivencia
    0.29
    ბ
    0.29
    存
    0.29
    ア
    0.29
    Activations Density 0.000%

    No Known Activations