© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37307
    Prev
    Next
    INDEX
    Explanations

    avoiding negative outcomes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    倝
    0.38
     enumer
    0.36
     concre
    0.35
    酽
    0.35
     kucing
    0.35
    Nathan
    0.34
     মাঝি
    0.33
    ^{\#}\
    0.33
    ल्लभ
    0.32
    ഞ്ചി
    0.32
    POSITIVE LOGITS
     Eventually
    0.35
    めます
    0.35
    かります
    0.35
     hiszen
    0.34
     Está
    0.34
    Если
    0.33
    اردوش
    0.33
    ąg
    0.33
    ln
    0.32
    ようになりました
    0.32
    Activations Density 0.080%

    No Known Activations