© 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
    2. Gemma-3-27B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 209758
    Prev
    Next
    INDEX
    Explanations

    I am a

    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_19_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
     Lie
    0.45
     thinks
    0.44
    AKER
    0.42
     TikTok
    0.42
     obtain
    0.41
     Search
    0.41
     S
    0.41
     search
    0.41
     Tranqu
    0.41
    さん
    0.41
    POSITIVE LOGITS
     ξε
    0.47
    carouselExample
    0.47
    疚
    0.45
     рекорд
    0.45
    etheless
    0.44
     trotzdem
    0.43
     ಗಾ
    0.43
     ఆర్థిక
    0.42
     conceding
    0.42
    clustering
    0.41
    Activations Density 0.005%

    No Known Activations