© 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. 217957
    Prev
    Next
    INDEX
    Explanations

    Coca-Cola Fanta Sprite

    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
    آ
    0.38
     آ
    0.37
     sve
    0.37
    ivided
    0.37
    </iframe>
    0.35
    ITT
    0.35
     ദൈ
    0.34
    pub
    0.34
    энер
    0.34
    
    0.34
    POSITIVE LOGITS
    SPs
    0.38
     Wur
    0.37
     mâ
    0.37
    uzzo
    0.37
     aspen
    0.36
     thus
    0.36
    erra
    0.35
     SP
    0.35
     spectator
    0.35
    धाना
    0.35
    Activations Density 0.099%

    No Known Activations