© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162561
    Prev
    Next
    INDEX
    Explanations

    end of clause or sentence

    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
     opening
    0.38
    씨
    0.38
     উদ্ব
    0.37
    opening
    0.37
     summary
    0.36
     supreme
    0.36
     pokemon
    0.35
     furious
    0.35
    pokemon
    0.34
    Pokémon
    0.34
    POSITIVE LOGITS
     Differ
    0.41
     менедже
    0.41
     Banj
    0.40
    经理
    0.38
    AMAN
    0.38
    rances
    0.36
    觞
    0.36
    管理人
    0.36
     मैनेज
    0.36
     Chez
    0.36
    Activations Density 0.001%

    No Known Activations