© 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. 162825
    Prev
    Next
    INDEX
    Explanations

    GPT

    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
     pater
    0.36
     corresponding
    0.34
     sores
    0.33
     cavities
    0.33
    Ange
    0.31
    itting
    0.31
    ارين
    0.31
    竪
    0.31
    শ্রেষ্ঠ
    0.30
     rugged
    0.30
    POSITIVE LOGITS
    യിരുന്നു
    0.35
     Umsetzung
    0.35
    ドル
    0.34
     اسٹ
    0.33
    Retro
    0.33
    ডিয়া
    0.32
     Drafting
    0.31
     Retro
    0.31
     हाला
    0.31
     Estate
    0.30
    Activations Density 0.040%

    No Known Activations