© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78279
    Prev
    Next
    INDEX
    Explanations

    World War II service members

    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
     appe
    0.40
    ቧ
    0.39
     appeal
    0.39
    ográf
    0.37
    Operational
    0.37
    opra
    0.36
     konflik
    0.35
     IUP
    0.35
     Boone
    0.34
    ɾ
    0.34
    POSITIVE LOGITS
     பரிசு
    0.42
     شركة
    0.40
    شركة
    0.37
    会社の
    0.37
     جمعه
    0.36
     কী
    0.36
    ificateur
    0.36
     packaging
    0.35
    assic
    0.35
     company
    0.34
    Activations Density 0.001%

    No Known Activations