© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196364
    Prev
    Next
    INDEX
    Explanations

    Social programs and voting

    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_27_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
    Communication
    0.41
    Prepared
    0.40
     Committed
    0.37
    Survived
    0.37
     कम्युनिकेशन
    0.37
     spokesperson
    0.37
    顺
    0.37
     matrimon
    0.36
    策
    0.36
     committed
    0.36
    POSITIVE LOGITS
     subsidies
    0.49
    កំណ
    0.43
     издание
    0.43
     Cadd
    0.41
     debat
    0.41
     retirees
    0.39
    凱
    0.38
     candy
    0.38
     неиз
    0.38
     ataupun
    0.38
    Activations Density 0.019%

    No Known Activations