© 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. 51618
    Prev
    Next
    INDEX
    Explanations

    dear [customer name]

    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
    镐
    0.41
     dolazi
    0.37
    čno
    0.37
     طراحی
    0.37
    無法
    0.37
    模块
    0.34
     ఉత్ప
    0.34
    규
    0.34
     forskellige
    0.34
    嚟
    0.33
    POSITIVE LOGITS
     moi
    0.38
    сер
    0.36
    Mir
    0.33
     mots
    0.33
     admitted
    0.31
    moi
    0.31
     HP
    0.31
     leader
    0.31
    zzle
    0.31
     totalité
    0.30
    Activations Density 0.000%

    No Known Activations