© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8712
    Prev
    Next
    INDEX
    Explanations

    media and web tools

    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_40_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
    孜
    0.37
    องค์การ
    0.37
     திரும
    0.37
     安全
    0.37
     கண்
    0.37
     Kriegs
    0.36
     Giving
    0.35
    Making
    0.35
    ⑫
    0.35
     기간
    0.35
    POSITIVE LOGITS
    靶
    0.41
    髏
    0.39
    pute
    0.38
    след
    0.37
     வாச
    0.37
    шается
    0.36
    intel
    0.36
    鋼
    0.36
    섯
    0.35
    霝
    0.35
    Activations Density 0.054%

    No Known Activations