© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 104808
    Prev
    Next
    INDEX
    Explanations

    wildlife or state agencies

    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_44_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
     fish
    0.55
     Fish
    0.54
    魚
    0.47
     मछली
    0.45
    Fish
    0.45
    鱼
    0.45
     wildlife
    0.43
     tipping
    0.41
     fished
    0.41
     hire
    0.40
    POSITIVE LOGITS
    тение
    0.44
    中止
    0.41
    Boot
    0.40
    弦
    0.39
    Loads
    0.38
    坫
    0.38
     lancéolées
    0.38
    Robin
    0.36
    paras
    0.36
    Beat
    0.36
    Activations Density 0.000%

    No Known Activations