© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124545
    Prev
    Next
    INDEX
    Explanations

    fatty fish

    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_37_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
     Osaka
    0.37
    英
    0.37
     ethylene
    0.37
    草原
    0.36
     வள்ளி
    0.36
     Flüss
    0.36
     ethane
    0.36
    PP
    0.35
     Vergangenheit
    0.35
     প্যার
    0.34
    POSITIVE LOGITS
     fish
    1.29
    Fish
    1.15
    鱼
    1.15
     fishes
    1.14
    魚
    1.13
     मछली
    1.10
     Fish
    1.07
    fish
    1.05
     মাছ
    1.04
    FISH
    1.00
    Activations Density 0.002%

    No Known Activations